Adaptive Segmentation Algorithm for Subtle Defect Images on the Surface of Magnetic Ring Using 2D-Gabor Filter Bank.

In order to realize the unsupervised segmentation of subtle defect images on the surface of small magnetic rings and improve the segmentation accuracy and computational efficiency, here, an adaptive threshold segmentation method is proposed based on the improved multi-scale and multi-directional 2D-Gabor filter bank. Firstly, the improved multi-scale and multi-directional 2D-Gabor filter bank was used to filter and reduce the noise on the defect image, suppress the noise pollution inside the target area and the background area, and enhance the difference between the magnetic ring defect and the background. Secondly, this study analyzed the grayscale statistical characteristics of the processed image; the segmentation threshold was constructed according to the gray statistical law of the image; and the adaptive segmentation of subtle defect images on the surface of small magnetic rings was realized. Finally, a classifier based on a BP neural network is designed to classify the scar images and crack images determined by different threshold segmentation methods. The classification accuracies of the iterative method, the OTSU method, the maximum entropy method, and the adaptive threshold segmentation method are, respectively, 85%, 87.5%, 95%, and 97.5%. The adaptive threshold segmentation method proposed in this paper has the highest classification accuracy. Through verification and comparison, the proposed algorithm can segment defects quickly and accurately and suppress noise interference effectively. It is better than other traditional image threshold segmentation methods, validated by both segmentation accuracy and computational efficiency. At the same time, the real-time performance of our algorithm was performed on the advanced SEED-DVS8168 platform.

Optimized Classification of Intelligent Reflecting Surface (IRS)-Enabled GEO Satellite Signals.

The intelligent reflecting surface (IRS) is a cutting-edge technology for cost-effectively achieving future spectrum- and energy-efficient wireless communication. In particular, an IRS comprises many low-cost passive devices that can independently reflect the incident signal with a configurable phase shift to produce three-dimensional (3D) passive beamforming without transmitting Radio-Frequency (RF) chains. Thus, the IRS can be utilized to greatly improve wireless channel conditions and increase the dependability of communication systems. This article proposes a scheme for an IRS-equipped GEO satellite signal with proper channel modeling and system characterization. Gabor filter networks (GFNs) are jointly proposed for the extraction of distinct features and the classification of these features. Hybrid optimal functions are used to solve the estimated classification problem, and a simulation setup was designed along with proper channel modeling. The experimental results show that the proposed IRS-based methodology provides higher classification accuracy than the benchmark without the IRS methodology.

Early detection of tuberculosis using hybrid feature descriptors and deep learning network.

Purpose: To detect tuberculosis (TB) at an early stage by analyzing chest X-ray images using a deep neural network, and to evaluate the efficacy of proposed model by comparing it with existing studies. Material and methods: For the study, an open-source X-ray images were used. Dataset consisted of two types of images, i.e., standard and tuberculosis. Total number of images in the dataset was 4,200, among which, 3,500 were normal chest X-rays, and the remaining 700 X-ray images were of tuberculosis patients. The study proposed and simulated a deep learning prediction model for early TB diagnosis by combining deep features with hand-engineered features. Gabor filter and Canny edge detection method were applied to enhance the performance and reduce computation cost. Results: The proposed model simulated two scenarios: without filter and edge detection techniques and only a pre-trained model with automatic feature extraction, and filter and edge detection techniques. The results achieved from both the models were 95.7% and 97.9%, respectively. Conclusions: The proposed study can assist in the detection if a radiologist is not available. Also, the model was tested with real-time images to examine the efficacy, and was better than other available models.

A New Feature Descriptor for Multimodal Image Registration Using Phase Congruency.

Images captured by different sensors with different spectral bands cause non-linear intensity changes between image pairs. Classic feature descriptors cannot handle this problem and are prone to yielding unsatisfactory results. Inspired by the illumination and contrast invariant properties of phase congruency, here, we propose a new descriptor to tackle this problem. The proposed descriptor generation mainly involves three steps. (1) Images are convolved with a bank of log-Gabor filters with different scales and orientations. (2) A window of fixed size is selected and divided into several blocks for each keypoint, and an oriented magnitude histogram and the orientation of the minimum moment of a phase congruency-based histogram are calculated in each block. (3) These two histograms are normalized respectively and concatenated to form the proposed descriptor. Performance evaluation experiments on three datasets were carried out to validate the superiority of the proposed method. Experimental results indicated that the proposed descriptor outperformed most of the classic and state-of-art descriptors in terms of precision and recall within an acceptable computational time.

Novel Local Coding Algorithm for Finger Multimodal Feature Description and Recognition.

Recently, finger-based biometrics, including fingerprint (FP), finger-vein (FV) and finger-knuckle-print (FKP) with high convenience and user friendliness, have attracted much attention for personal identification. The features expression which is insensitive to illumination and pose variation are beneficial for finger trimodal recognition performance improvement. Therefore, exploring suitable method of reliable feature description is of great significance for developing finger-based biometric recognition system. In this paper, we first propose a correction approach for dealing with the pose inconsistency among the finger trimodal images, and then introduce a novel local coding-based feature expression method to further implement feature fusion of FP, FV, and FKP traits. First, for the coding scheme a bank of oriented Gabor filters is used for direction feature enhancement in finger images. Then, a generalized symmetric local graph structure (GSLGS) is developed to fully express the position and orientation relationships among neighborhood pixels. Experimental results on our own-built finger trimodal database show that the proposed coding-based approach achieves excellent performance in improving the matching accuracy and recognition efficiency.

A method of localization and segmentation of intervertebral discs in spine MRI based on Gabor filter bank.

BACKGROUND: Spine magnetic resonance image (MRI) plays a very important role in the diagnosis of various spinal diseases, such as disc degeneration, scoliosis, and osteoporosis. Accurate localization and segmentation of the intervertebral disc (IVD) in spine MRI can help accelerate the diagnosis time and assist in the treatment by providing quantitative parameters. In this paper, a method based on Gabor filter bank is proposed for IVD localization and segmentation. METHODS: First, the structural features of IVDs are extracted using a Gabor filter bank. Second, the Gabor features of spine are calculated and spinal curves are detected. Third, the Gabor feature images (GFI) of IVDs are calculated and adjusted according to the spinal curves. Fourth, the IVDs are localized by clustering analysis with GFI. Finally, an optimum grayscale-based algorithm with self-adaptive threshold, combined with the localization results and Gabor features of the spine, is performed for IVDs segmentation. RESULTS: The proposed method is verified by an MRI dataset consisting of 278 IVDs from 37 patients. The accuracy of localization is 98.23 % and the dice similarity index for segmentation evaluation is 0.9237. CONCLUSIONS: The proposed Gabor filter based method is effective for IVD localization and segmentation. It would be useful in computer-aided diagnosis of IVD diseases and computer-assisted spine surgery.

Head Pose Estimation on Top of Haar-Like Face Detection: A Study Using the Kinect Sensor.

Head pose estimation is a crucial initial task for human face analysis, which is employed in several computer vision systems, such as: facial expression recognition, head gesture recognition, yawn detection, etc. In this work, we propose a frame-based approach to estimate the head pose on top of the Viola and Jones (VJ) Haar-like face detector. Several appearance and depth-based feature types are employed for the pose estimation, where comparisons between them in terms of accuracy and speed are presented. It is clearly shown through this work that using the depth data, we improve the accuracy of the head pose estimation. Additionally, we can spot positive detections, faces in profile views detected by the frontal model, that are wrongly cropped due to background disturbances. We introduce a new depth-based feature descriptor that provides competitive estimation results with a lower computation time. Evaluation on a benchmark Kinect database shows that the histogram of oriented gradients and the developed depth-based features are more distinctive for the head pose estimation, where they compare favorably to the current state-of-the-art approaches. Using a concatenation of the aforementioned feature types, we achieved a head pose estimation with average errors not exceeding 5:1; 4:6; 4:2 for pitch, yaw and roll angles, respectively.

Contour extracting networks in early extrastriate cortex.

Neurons in the visual cortex process a local region of visual space, but in order to adequately analyze natural images, neurons need to interact. The notion of an ''association field'' proposes that neurons interact to extract extended contours. Here, we identify the site and properties of contour integration mechanisms. We used functional magnetic resonance imaging (fMRI) and population receptive field (pRF) analyses. We devised pRF mapping stimuli consisting of contours. We isolated the contribution of contour integration mechanisms to the pRF by manipulating the contour content. This stimulus manipulation led to systematic changes in pRF size. Whereas a bank of Gabor filters quantitatively explains pRF size changes in V1, only V2/V3 pRF sizes match the predictions of the association field. pRF size changes in later visual field maps, hV4, LO-1, and LO-2 do not follow either prediction and are probably driven by distinct classical receptive field properties or other extraclassical integration mechanisms. These pRF changes do not follow conventional fMRI signal strength measures. Therefore, analyses of pRF changes provide a novel computational neuroimaging approach to investigating neural interactions. We interpreted these results as evidence for neural interactions along cooriented, cocircular receptive fields in the early extrastriate visual cortex (V2/V3), consistent with the notion of a contour association field.

Physics-informed neural wavefields with Gabor basis functions.

Recently, Physics-Informed Neural Networks (PINNs) have gained significant attention for their versatile interpolation capabilities in solving partial differential equations (PDEs). Despite their potential, the training can be computationally demanding, especially for intricate functions like wavefields. This is primarily due to the neural-based (learned) basis functions, biased toward low frequencies, as they are dominated by polynomial calculations, which are not inherently wavefield-friendly. In response, we propose an approach to enhance the efficiency and accuracy of neural network wavefield solutions by modeling them as linear combinations of Gabor basis functions that satisfy the wave equation. Specifically, for the Helmholtz equation, we augment the fully connected neural network model with an adaptable Gabor layer constituting the final hidden layer, employing a weighted summation of these Gabor neurons to compute the predictions (output). These weights/coefficients of the Gabor functions are learned from the previous hidden layers that include nonlinear activation functions. To ensure the Gabor layer's utilization across the model space, we incorporate a smaller auxiliary network to forecast the center of each Gabor function based on input coordinates. Realistic assessments showcase the efficacy of this novel implementation compared to the vanilla PINN, particularly in scenarios involving high-frequencies and realistic models that are often challenging for PINNs.

Gabor filter-based statistical features for ADHD detection.

Attention deficit/hyperactivity disorder (ADHD) is a neuropsychological disorder that occurs in children and is characterized by inattention, impulsivity, and hyperactivity. Early and accurate diagnosis of ADHD is very important for effective intervention. The aim of this study is to develop a computer-aided approach to detecting ADHD using electroencephalogram (EEG) signals. Specifically, we explore a Gabor filter-based statistical features approach for the classification of EEG signals into ADHD and healthy control (HC). The EEG signal is processed by a bank of Gabor filters to obtain narrow-band signals. Subsequently, a set of statistical features is extracted. The computed features are then subjected to feature selection. Finally, the obtained feature vector is given to a classifier to detect ADHD and HC. Our approach achieves the highest classification accuracy of 96.4% on a publicly available dataset. Furthermore, our approach demonstrates better classification accuracy than the existing methods.

Precancerous Change Detection Technique on Mammography Breast Cancer Images based on Mean Ratio and Log Ratio using Fuzzy c Mean Classification with Gabor Filter.

BACKGROUND: The growing rate of breast cancer necessitates immediate global attention. Mammography images are used to determine the stage of malignancy. Breast cancer stages must be identified in order to save a person's life. OBJECTIVE: This article's main goal is to identify different techniques to obtain the difference between two breast cancer mammography images taken of the same individual at different times. This is the first effort to identify breast cancer in mammography images using change detection techniques. The Mammogram Image Change Detection (ICD) technique is also a recent advancement to prevent breast cancer in the early stage and precancerous level in medical images. METHODS: The main purpose of this work is to observe the changes between breast cancer images in different screening periods using different techniques. Mammogram Breast Cancer Image Change Detection (MBCICD) methods usually start with a Difference Image (DI) and classify the pixels in the DI into changed and unaffected classes using unsupervised fuzzy c means (FCM) clustering methods based on texture features taken from the log and mean ratio difference pictures. Two operators, mean ratio and log ratio, were used to check the changes in the images. The Gabor wavelet is utilized as a feature extraction technique among several standards. Using the Gabor wavelet ratio operators is a useful method for altering the detection of breast cancer in mammography images. Currently, it is challenging to obtain real malignant images of the same person for testing or training. In this study, two images are utilized. To clearly see the changes, one is an image from the MIAS breast cancer mammography images dataset, and the other is a self-generated change image. RESULTS: The research aims to examine the image results and other quantitative analysis results of proposed change detection methods on cancer images. The Mean Ratio Accuracy result is 0.9738, and the Log ratio PCC is 0.9737. The classification results are the Log Ratio + Gabor Filter + FCM is 0.9737, and Mean Ratio +Gabor Filter + FCM is 0.9719. The mean Ratio Accuracy result is 0.9738, Log ratio is 0.9737. Log Ratio + Gabor Filter + FCM is 0.9737, Mean Ratio +Gabor Filter + FCM is 0.9719. Comparing the PCC of proposed change detection methods with the FDA-RMG method on the same dataset, the accuracy is 0.9481 only. CONCLUSION: The study concludes that variations in mammography breast cancer images could be successfully identified using the ratio operators with Gabor wavelet features.

Augmenting Aquaculture Efficiency through Involutional Neural Networks and Self-Attention for Oplegnathus Punctatus Feeding Intensity Classification from Log Mel Spectrograms.

Understanding the feeding dynamics of aquatic animals is crucial for aquaculture optimization and ecosystem management. This paper proposes a novel framework for analyzing fish feeding behavior based on a fusion of spectrogram-extracted features and deep learning architecture. Raw audio waveforms are first transformed into Log Mel Spectrograms, and a fusion of features such as the Discrete Wavelet Transform, the Gabor filter, the Local Binary Pattern, and the Laplacian High Pass Filter, followed by a well-adapted deep model, is proposed to capture crucial spectral and spectral information that can help distinguish between the various forms of fish feeding behavior. The Involutional Neural Network (INN)-based deep learning model is used for classification, achieving an accuracy of up to 97% across various temporal segments. The proposed methodology is shown to be effective in accurately classifying the feeding intensities of Oplegnathus punctatus, enabling insights pertinent to aquaculture enhancement and ecosystem management. Future work may include additional feature extraction modalities and multi-modal data integration to further our understanding and contribute towards the sustainable management of marine resources.

Fingerprint image enhancement using multiple filters.

Biometrics is the measurement of an individual's distinctive physical and behavioral characteristics. In comparison to traditional token-based or knowledge-based forms of identification, biometrics such as fingerprints, are more reliable. Fingerprint images recorded digitally can be affected by scanner noise, incorrect finger pressure, condition of the finger's skin (wet, dry, or abraded), or physical material it is scanned from. Image enhancement algorithms applied to fingerprint images remove noise elements while retaining relevant structures (ridges, valleys) and help in the detection of fingerprint features (minutiae). Amongst the most common image enhancement filters is the Gabor filter, however, given their restricted maximum bandwidth as well as limited range of spectral information, it falls short. We put forward a novel method of fingerprint image enhancement using a combination of a diffusion-coherence filter and a 2D log-Gabor filter. The log-Gabor overcomes the limitations of the Gabor filter while Coherence Diffusion mitigates noise elements within fingerprint images. Implementation is done on the FVC image database and assessed via visual comparison with coherence diffusion used disjointedly and with the Gabor filter.

Lumbar intervertebral disc segmentation for computer modeling and simulation.

BACKGROUND AND OBJECTIVE: The present work had as its main objective the development of a method for localizing and automatically segmenting lumbar intervertebral discs (IVD) in 3D from magnetic resonance imaging (MRI), with the goal of supporting the generation of finite element (FE) models from actual lumbar spine anatomy, by providing accurate and personalized information on the shape of the patient's IVD. The extension of the method to allow performing separate segmentations of the IVD's two main structures - annulus fibrosus (AF) and nucleus pulposus (NP) - as well as automatically detecting degenerated IVD where this distinction is no longer possible was also an objective of the work. METHODS: The method presented here evolves from 2D segmentations in the sagittal profile using Gabor filters towards 3D segmentations. It works by detecting the spine curves and intensity regions corresponding to IVD. As so, the 2D method from Zhu et al. (2013) was partially implemented, modified and adapted to 3D use, and then tested with eight spines from two separated online datasets. The 3D adaptation was achieved by using vertebral body segmentation masks to approximate the shape of the vertebrae and to adjust the spine curves accordingly. RESULTS: The method showed average values of 85%, 83% and 96% for the Dice coefficient, sensitivity and specificity, respectively. The method correctly identified 65 of 68 (96%) IVD as either healthy or degenerated. The method's Dice coefficient is within the range of existing 3D IVD segmentation methods in the literature (81-92%). The method took on average 6-7 s to perform a full 3D segmentation, which is well within the range of the existing methods (2 s - 19 min). CONCLUSIONS: The developed method can be used to generate accurate 3D models of the IVD based on MRI, with AF/NP distinction and detection of marked degeneration by comparing each IVD with the remaining spine levels. Further work shall improve the method towards distinguishing between specific levels of degeneration for clinically oriented FE modeling.

An effective fingerprint orientation field estimation method using differential values of grayscale intensity.

Fingerprint orientation field (OF) estimation is important for basic fingerprint image processing and impacts the accuracy of fingerprint image enhancements, such as Gabor filters. In this article, we introduce an OF estimation algorithm based on differential values of grayscale intensity and examine the accuracy and reliability of the proposed algorithm by applying it to fingerprint images processed using Gaussian blurring and the Gaussian white noise process. The experimental results indicate that the OF estimation reliability of the proposed algorithm is higher than the gradient-based method and the power spectral density (PSD) based method in low quality fingerprints. The proposed algorithm is especially useful in noisy fingerprint images, where the OF estimation reliability of the algorithm is 6.46% and 32.93% higher than the gradient-based method and the PSD-based method, respectively.

Discriminant Analysis Using Gabor Filter Sets for Lobular Endocervical Glandular Hyperplasia: Numerical Interpretation of Nuclear Atypia by Gabor Filter Features.

INTRODUCTION: Lobular endocervical glandular hyperplasia (LEGH) is a benign lesion; however, it is considered to be the origin of gastric-type adenocarcinoma in the uterine cervix, and early diagnosis is important. At Shinshu University Hospital, screening of LEGH cells is based on the difference in color tone of cytoplasmic mucin on Papanicolaou staining and detection of gastric mucin using HIK1083-labeled latex agglutination assay. However, it is sometimes difficult to distinguish LEGH cells with subtle nuclear atypia from endocervical (EC) cells. METHODS: We calculated the Gabor filter features (mean signal value, standard deviation, skewness, kurtosis) from the nuclei of cytological specimens in EC cells (37 cases) and LEGH cells (33 cases) using microscopic images, and we performed statistical analysis and discriminant analysis by linear support vector machine (LSVM) using these features. A Gabor filter is a linear filter defined as a mathematical representation of the mammalian visual system. Gabor filters with three wavelengths and eight angles were used for analysis. RESULTS: Gabor filter features in EC cells were higher than in LEGH cells, demonstrating that the gradient of LEGH cell nuclei was milder than that of EC cell nuclei. The accuracy calculated using all Gabor filters was 91.0% and the accuracy of four Gabor filters (λ = 2/3π and θ = 0°, 45°, 90°, 135°) was 88.9%. High accuracy with low computation costs was achieved by reducing the number of features used for LSVM. CONCLUSION: The application of a Gabor filter with convolutional processing resulted in the edges of LEGH cells being slightly rough and thick, whereas those of EC cells were fine and thin. Thus, it is thought that the frequency of abrupt gradients of pixels was higher in EC cells than in LEGH cells, and the gradient of chromatin distribution in LEGH cell nuclei was milder than that in EC cell nuclei. It was possible to evaluate nuclear findings of EC and LEGH cells objectively by quantifying morphological features of nuclei using Gabor filters. It was possible to differentiate EC cells from LEGH cells using LSVM using Gabor filter features.

Performance analysis of reshaped Gabor filter for removing the Rician distributed noise in brain MR images.

Magnetic Resonance Imaging (MRI) is an essential clinical tool for detecting the abnormalities such as tumors and clots in the human brain. The brain MR images are contaminated by artifacts and noise that follow Rician distribution during the acquisition process. It causes the loss of fine details information, distortion, and a blurred vision of the image. A reshaped Gabor filter-based denoising technique is proposed to overcome these issues. To develop the reshaped Gabor filter, the range of reshaping parameters of the filter is initially obtained by a random search method. Further, to evaluate the better performance of the proposed filter, a manual search is used to find the optimal parametric values and tested on T1, T2, and PD weighted MR data sets one by one. Also, the proposed technique is compared with the existing state of the art filtering methods such as Wiener, Median, Partial differential equation (PDE), Anisotropic diffusion filter (ADF), Non-local means filter (NLM), Modified complex diffusion filter (MCD), Multichannel residual learning of CNN (MRL), Maximum a posteriori (MAP), Adaptive non-local means algorithm (ADNLM), and Advance NLM filtering with non-sub sampled (AVNLMNS) on the basic reference and no reference parameter. The parameters such as mean square error (MSE), peak signal to noise ratio (PSNR), structural similarity index metric (SSIM), perception-based image quality evaluator (PIQE), and blind/referenceless image spatial quality evaluator (BRISQE) are evaluated on T1, T2, and PD weighted MR images with different noise variances such as 1%, 3%, 5%, 7%, and 9%. The proposed method may be used as a better denoising scheme for Rician distributed noise, edge preservation, fine details restoration, and enhancement of abnormalities.

GaborNet: investigating the importance of color space, scale and orientation for image classification.

Content-Based Image Retrieval (CBIR) is the cornerstone of today's image retrieval systems. The most distinctive retrieval approach used, involves the submission of an image-based query whereby the system is used in the extraction of visual characteristics like the shape, color, and texture from the images. Examination of the characteristics is done for ensuring the searching and retrieval of proportional images from the image database. Majority of the datasets utilized for retrieval lean towards to comprise colored images. The colored images are regarded as in RGB (Red, Green, Blue) form. Most colored images use the RGB image for classifying the images. The research presents the transformation of RGB to other color spaces, extraction of features using different color spaces techniques, Gabor filter and use Convolutional Neural Networks for retrieval to find the most efficient combination. The model is also known as Gabor Convolution Network. Even though the notion of the Gabor filter being induced in CNN has been suggested earlier, this work introduces an entirely different and very simple Gabor-based CNN which produces high recognition efficiency. In this paper, Gabor Convolutional Networks (GCNs or GaborNet), with different color spaces are used to examine which combination is efficient to retrieve natural images. An extensive experiment using Cifar 10 dataset was made and comparison of simple CNN, ResNet 50 and GCN model was also made. The models were evaluated through a several statistical analysis based on accuracy, precision, recall, F-Score, area under the curve (AUC), and receiving operating characteristic (ROC) curve. The results shows GaborNet model effectively retrieve images with 99.68% of AUC and 99.09% of Recall. The results also shows different images are effectively retrieved using different color space. Therefore research concluded it is very significance to transform images to different color space and use GaborNet for effective retrieval.

Automated screening of COVID-19 using two-dimensional variational mode decomposition and locally linear embedding.

In order to aid imaging physicians to effectively screen chest radiography medical images for presence of Coronavirus Disease 2019 (COVID-19), a novel computer aided diagnosis technology for automatic processing of COVID-19 images is proposed based on two-dimensional variational mode decomposition (2D-VMD) and locally linear embedding (LLE). 2D-VMD algorithm is used to decompose normal and COVID-19 images, and then feature extraction of intrinsic mode functions (IMFs) using Gabor filter. To better extract low-dimensional parameters which are useful for COVID-19 diagnosis, the performance of two dimensionality reduction techniques of principal component analysis (PCA) and LLE are compared, and the LLE is shown to offer satisfactory effect of dimension reduction. Thereafter, the particle swarm optimization-support vector machine (PSO-SVM) algorithm is used to classify. The simulation results show that the proposed technology has achieved accuracy of 99.33%, precision of 100%, recall of 98.63% and F-Measure of 99.31%. Hence, the developed diagnosis technology can be used as an important auxiliary tool to assist diagnosis of imaging physicians.

Biological convolutions improve DNN robustness to noise and generalisation.

Deep Convolutional Neural Networks (DNNs) have achieved superhuman accuracy on standard image classification benchmarks. Their success has reignited significant interest in their use as models of the primate visual system, bolstered by claims of their architectural and representational similarities. However, closer scrutiny of these models suggests that they rely on various forms of shortcut learning to achieve their impressive performance, such as using texture rather than shape information. Such superficial solutions to image recognition have been shown to make DNNs brittle in the face of more challenging tests such as noise-perturbed or out-of-distribution images, casting doubt on their similarity to their biological counterparts. In the present work, we demonstrate that adding fixed biological filter banks, in particular banks of Gabor filters, helps to constrain the networks to avoid reliance on shortcuts, making them develop more structured internal representations and more tolerance to noise. Importantly, they also gained around 20-35% improved accuracy when generalising to our novel out-of-distribution test image sets over standard end-to-end trained architectures. We take these findings to suggest that these properties of the primate visual system should be incorporated into DNNs to make them more able to cope with real-world vision and better capture some of the more impressive aspects of human visual perception such as generalisation.