[Multi-feature Extraction and Classification of Breast Tumor in Ultrasound Image].

OBJECTIVE: Feature extraction of breast tumors is very important in the breast tumor detection (benign and malignant) in ultrasound image. The traditional quantitative description of breast tumors has some shortcomings, such as inaccuracy. A simple and accurate feature extraction method has been studied. METHODS: In this paper, a new method of boundary feature extraction was proposed. Firstly, the shape histogram of ultrasound breast tumors was constructed. Secondly, the relevant boundary feature factors were calculated from a local point of view, including sum of maximum curvature, sum of maximum curvature and peak, sum of maximum curvature and standard deviation. Based on the boundary features, shape features and texture features, the linear support vector machine classifiers for benign and malignant breast tumor recognition was constructed. RESULTS: The accuracy of boundary features in the benign and malignant breast tumors classification was 82.69%. The accuracy of shape features was 73.08%. The accuracy of texture features was 63.46%. The classification accuracy of the three fusion features was 86.54%. CONCLUSIONS: The classification accuracy of boundary features was higher than that of texture features and shape features. The classification method based on multi-features has the highest accuracy and it describes the benign and malignant tumors from different angles. The research results have practical value.

Radiogenomics of lower-grade glioma: algorithmically-assessed tumor shape is associated with tumor genomic subtypes and patient outcomes in a multi-institutional study with The Cancer Genome Atlas data.

Recent studies identified distinct genomic subtypes of lower-grade gliomas that could potentially be used to guide patient treatment. This study aims to determine whether there is an association between genomics of lower-grade glioma tumors and patient outcomes using algorithmic measurements of tumor shape in magnetic resonance imaging (MRI). We analyzed preoperative imaging and genomic subtype data from 110 patients with lower-grade gliomas (WHO grade II and III) from The Cancer Genome Atlas. Computer algorithms were applied to analyze the imaging data and provided five quantitative measurements of tumor shape in two and three dimensions. Genomic data for the analyzed cohort of patients consisted of previously identified genomic clusters based on IDH mutation and 1p/19q co-deletion, DNA methylation, gene expression, DNA copy number, and microRNA expression. Patient outcomes were quantified by overall survival. We found that there is a strong association between angular standard deviation (ASD), which measures irregularity of the tumor boundary, and the IDH-1p/19q subtype (p < 0.0017), RNASeq cluster (p < 0.0002), DNA copy number cluster (p < 0.001), and the cluster of clusters (p < 0.0002). The RNASeq cluster was also associated with bounding ellipsoid volume ratio (p < 0.0005). Tumors in the IDH wild type cluster and R2 RNASeq cluster which are associated with much poorer outcomes generally had higher ASD reflecting more irregular shape. ASD also showed association with patient overall survival (p = 0.006). Shape features in MRI were strongly associated with genomic subtypes and patient outcomes in lower-grade glioma.

Can Only the Shape Feature in Radiomics Help Machine Learning Show That Bladder Cancer Has Invaded Muscles?

OBJECTIVES: The presence of muscle invasion is an important factor in establishing a treatment strategy for bladder cancer (BCa). The aim of this study is to reveal the diagnostic performance of radiomic shape features in predicting muscle-invasive BCa. METHODS: In this study, 60 patients with histologically proven BCa who underwent a preoperative MRI were retrospectively recruited. The whole tumor volume was segmented on apparent diffusion coefficient (ADC) maps and T2W images. Afterward, the shape features of the volume of interest were extracted using PyRadiomics. Machine learning classification was performed using statistically different shape features in MATLAB® (The MathWorks, Inc., Natick, Massachusetts, United States). RESULTS: The findings revealed that 27 bladder cancer patients had muscle invasion, while 33 had superficial bladder cancer (53 men and seven women; mean age: 62±14). Surface area, volume, and relevant features were significantly greater in the invasive group than in the non-invasive group based on the ADC maps (P<0.05). Superficial bladder cancer had a more spherical form compared to invasive bladder cancer (P=0.05) with both imaging modalities. Flatness and elongation did not differ significantly between groups with either modality (P>0.05). Logistic regression had the highest accuracy of 83.3% (sensitivity 82.8%, specificity 84%) in assessing invasion based on the shape features of ADC maps, while K-nearest neighbors had the highest accuracy of 78.2% (sensitivity 79.1%, specificity 69.4%) in assessing invasion based on T2W images. CONCLUSIONS: Shape features can be helpful in predicting muscle invasion in bladder cancer using machine learning methods.

Prediction of Conversion from Mild Cognitive Impairment to Alzheimer's Disease Using Amyloid PET and Brain MR Imaging Data: A 48-Month Follow-Up Analysis of the Alzheimer's Disease Neuroimaging Initiative Cohort.

We developed a novel quantification method named "shape feature" by combining the features of amyloid positron emission tomography (PET) and brain magnetic resonance imaging (MRI) and evaluated its significance in predicting the conversion from mild cognitive impairment (MCI) to Alzheimer's disease (AD) in the Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort. From the ADNI database, 334 patients with MCI were included. The brain amyloid smoothing score (AV45_BASS) and brain atrophy index (MR_BAI) were calculated using the surface area and volume of the region of interest in AV45 PET and MRI. During the 48-month follow-up period, 108 (32.3%) patients converted from MCI to AD. Age, Mini-Mental State Examination (MMSE), cognitive subscale of the Alzheimer's Disease Assessment Scale (ADAS-cog), apolipoprotein E (APOE), standardized uptake value ratio (SUVR), AV45_BASS, MR_BAI, and shape feature were significantly different between converters and non-converters. Univariate analysis showed that age, MMSE, ADAS-cog, APOE, SUVR, AV45_BASS, MR_BAI, and shape feature were correlated with the conversion to AD. In multivariate analyses, high shape feature, SUVR, and ADAS-cog values were associated with an increased risk of conversion to AD. In patients with MCI in the ADNI cohort, our quantification method was the strongest prognostic factor for predicting their conversion to AD.

Combine EfficientNet and CNN for 3D model classification.

With the development of multimedia technology, the number of 3D models on the web or in databases is becoming increasingly larger and larger. It becomes more and more important to classify and retrieve 3D models. 3D model classification plays important roles in the mechanical design field, education field, medicine field and so on. Due to the 3D model's complexity and irregularity, it is difficult to classify 3D model correctly. Many methods of 3D model classification pay attention to local features from 2D views and neglect the 3D model's contour information, which cannot express it better. So, accuracy the of 3D model classification is poor. In order to improve the accuracy of 3D model classification, this paper proposes a method based on EfficientNet and Convolutional Neural Network (CNN) to classify 3D models, in which view feature and shape feature are used. The 3D model is projected into 2D views from different angles. EfficientNet is used to extract view feature from 2D views. Shape descriptors D1, D2, D3, Zernike moment and Fourier descriptors of 2D views are adopted to describe the 3D model and CNN is applied to extract shape feature. The view feature and shape feature are combined as discriminative features. Then, the softmax function is used to determine the 3D model's category. Experiments are conducted on ModelNet 10 dataset. Experimental results show that the proposed method achieves better than other methods.

Classification of fruits using computer vision and a multiclass support vector machine.

Automatic classification of fruits via computer vision is still a complicated task due to the various properties of numerous types of fruits. We propose a novel classification method based on a multi-class kernel support vector machine (kSVM) with the desirable goal of accurate and fast classification of fruits. First, fruit images were acquired by a digital camera, and then the background of each image was removed by a split-and-merge algorithm; Second, the color histogram, texture and shape features of each fruit image were extracted to compose a feature space; Third, principal component analysis (PCA) was used to reduce the dimensions of feature space; Finally, three kinds of multi-class SVMs were constructed, i.e., Winner-Takes-All SVM, Max-Wins-Voting SVM, and Directed Acyclic Graph SVM. Meanwhile, three kinds of kernels were chosen, i.e., linear kernel, Homogeneous Polynomial kernel, and Gaussian Radial Basis kernel; finally, the SVMs were trained using 5-fold stratified cross validation with the reduced feature vectors as input. The experimental results demonstrated that the Max-Wins-Voting SVM with Gaussian Radial Basis kernel achieves the best classification accuracy of 88.2%. For computation time, the Directed Acyclic Graph SVMs performs swiftest.

Discriminative Shape Feature Pooling in Deep Neural Networks.

Although deep learning approaches are able to generate generic image features from massive labeled data, discriminative handcrafted features still have advantages in providing explicit domain knowledge and reflecting intuitive visual understanding. Much of the existing research focuses on integrating both handcrafted features and deep networks to leverage the benefits. However, the issues of parameter quality have not been effectively solved in existing applications of handcrafted features in deep networks. In this research, we propose a method that enriches deep network features by utilizing the injected discriminative shape features (generic edge tokens and curve partitioning points) to adjust the network's internal parameter update process. Thus, the modified neural networks are trained under the guidance of specific domain knowledge, and they are able to generate image representations that incorporate the benefits from both handcrafted and deep learned features. The comparative experiments were performed on several benchmark datasets. The experimental results confirmed our method works well on both large and small training datasets. Additionally, compared with existing models using either handcrafted features or deep network representations, our method not only improves the corresponding performance, but also reduces the computational costs.

The coronal plane maximum diameter of deep intracerebral hemorrhage predicts functional outcome more accurately than hematoma volume.

BACKGROUND: Among prognostic imaging variables, the hematoma volume on admission computed tomography (CT) has long been considered the strongest predictor of outcome and mortality in intracerebral hemorrhage. AIMS: To examine whether different features of hematoma shape are associated with functional outcome in deep intracerebral hemorrhage. METHODS: We analyzed 790 patients from the ATACH-2 trial, and 14 shape features were quantified. We calculated Spearman's Rho to assess the correlation between shape features and three-month modified Rankin scale (mRS) score, and the area under the receiver operating characteristic curve (AUC) to quantify the association between shape features and poor outcome defined as mRS>2 as well as mRS > 3. RESULTS: Among 14 shape features, the maximum intracerebral hemorrhage diameter in the coronal plane was the strongest predictor of functional outcome, with a maximum coronal diameter >∼3.5 cm indicating higher three-month mRS scores. The maximum coronal diameter versus hematoma volume yielded a Rho of 0.40 versus 0.35 (p = 0.006), an AUC[mRS>2] of 0.71 versus 0.68 (p = 0.004), and an AUC[mRS>3] of 0.71 versus 0.69 (p = 0.029). In multiple regression analysis adjusted for known outcome predictors, the maximum coronal diameter was independently associated with three-month mRS (p < 0.001). CONCLUSIONS: A coronal-plane maximum diameter measurement offers greater prognostic value in deep intracerebral hemorrhage than hematoma volume. This simple shape metric may expedite assessment of admission head CTs, offer a potential biomarker for hematoma size eligibility criteria in clinical trials, and may substitute volume in prognostic intracerebral hemorrhage scoring systems.

Augmented reality calibration using feature triangulation iteration-based registration for surgical navigation.

BACKGROUND: Marker-based augmented reality (AR) calibration methods for surgical navigation often require a second computed tomography scan of the patient, and their clinical application is limited due to high manufacturing costs and low accuracy. METHODS: This work introduces a novel type of AR calibration framework that combines a Microsoft HoloLens device with a single camera registration module for surgical navigation. A camera is used to gather multi-view images of a patient for reconstruction in this framework. A shape feature matching-based search method is proposed to adjust the size of the reconstructed model. The double clustering-based 3D point cloud segmentation method and 3D line segment detection method are also proposed to extract the corner points of the image marker. The corner points are the registration data of the image marker. A feature triangulation iteration-based registration method is proposed to quickly and accurately calibrate the pose relationship between the image marker and the patient in the virtual and real space. The patient model after registration is wirelessly transmitted to the HoloLens device to display the AR scene. RESULTS: The proposed approach was used to conduct accuracy verification experiments on the phantoms and volunteers, which were compared with six advanced AR calibration methods. The proposed method obtained average fusion errors of 0.70 ± 0.16 and 0.91 ± 0.13 mm in phantom and volunteer experiments, respectively. The fusion accuracy of the proposed method is the highest among all comparison methods. A volunteer liver puncture clinical simulation experiment was also conducted to show the clinical feasibility. CONCLUSIONS: Our experiments proved the effectiveness of the proposed AR calibration method, and revealed a considerable potential for improving surgical performance.

An Intelligent Detector for Sensing Pork Freshness In Situ Based on a Multispectral Technique.

Fresh pork is prone to spoilage during storage, transportation, and sale, resulting in reduced freshness. The total viable count (TVC) and total volatile basic nitrogen (TVB-N) content are key indicators for evaluating the freshness of fresh pork, and when they reach unacceptable limits, this seriously threatens dietary safety. To realize the on-site, low-cost, rapid, and non-destructive testing and evaluation of fresh pork freshness, a miniaturized detector was developed based on a cost-effective multi-channel spectral sensor. The partial least squares discriminant analysis (PLS-DA) model was used to distinguish fresh meat from deteriorated meat. The detector consists of microcontroller, light source, multi-channel spectral sensor, heat-dissipation modules, display system, and battery. In this study, the multispectral data of pork samples with different freshness levels were collected by the developed detector, and its ability to distinguish pork freshness was based on different spectral shape features (SSF) (spectral ratio (SR), spectral difference (SD), and normalized spectral intensity difference (NSID)) were compared. The experimental results show that compared with the original multispectral modeling, the performance of the model based on spectral shape features is significantly improved. The model established by optimizing the spectral shape feature variables has the best performance, and the discrimination accuracy of its prediction set is 91.67%. In addition, the validation accuracy of the optimal model was 86.67%, and its sensitivity and variability were 87.50% and 85.71%, respectively. The results show that the detector developed in this study is cost-effective, compact in its structure, stable in its performance, and suitable for the on-site digital rapid non-destructive testing of freshness during the storage, transportation, and sale of fresh pork.

A hybrid method for biometric authentication-oriented face detection using autoregressive model with Bayes Backpropagation Neural Network.

This paper proposes a novel method, which is coined as ARBBPNN, for biometric-oriented face detection, based on autoregressive model with Bayes backpropagation neural network (BBPNN). Firstly, the given input colour key face image is modelled to HSV and YCbCr models. A hybrid model, called HS-YCbCr, is formulated based on the HSV and YCbCr models. The submodel, H, is divided into various sliding windows of size, 3 × 3. The model parameters are estimated for the window using the BBPNN. Based on the model coefficients, autocorrelation coefficients (ACCs) are computed. An autocorrelation test tests the significance of the ACCs. If the ACC passes the test, then it is inferred that the small image region, viz. the window, represents the texture and it is treated as the texture feature. Otherwise, it is regarded as structure, which is treated as the shape feature. The texture and shape features are formulated as feature vectors (FV) separately, and they are combined into a single FV. This process is performed for all colour submodels. The FVs of the submodels are combined into a single holistic vector, which is treated as the FV of the key face image. The key FV has twenty feature elements. The similarity of the key and target face images is examined, based on the key and target FVs, by deploying multivariate parametric statistical tests. If the FVs of the key and target images pass the tests, then it is concluded that the key and target face images are the same; otherwise, they are regarded as different. The GT, FSW, Pointing'04, and BioID datasets are considered for the experiments. In addition to the above datasets, we have constructed a dataset with face images collected from Google, and many images captured through a digital camera. It is also subjected to the experiment. The obtained recognition results show that the proposed ARBBPNN method outperforms the existing methods.

Breast mass classification on sonographic images on the basis of shape analysis.

PURPOSE: To evaluate the efficiency of novel shape features for classification of benign and malignant sonographic breast masses. METHODS: Mass regions were extracted from the region of interest (ROI) sub-image by applying a segmentation algorithm based on the level set method. Six features (difference area with five features of mass pixel number viewed at different angles) were then extracted for further classification. A multilayered perceptron neural network (MLP) classifier was used to classify breast mass. The leave-one-case-out procedure was used on a database of 81 pathologically proved breast sonographic images of patients (47 benign cases and 34 malignant cases) to evaluate our method. RESULTS: The classification results showed overall accuracy was 93.83%, sensitivity 91.18%, specificity 95.74%, positive predictive value 93.94%, and negative predictive value 93.75%. CONCLUSION: The experimental results showed that this diagnostic system with the features proposed can improve the positive rate of biopsies, provide a second opinion for physicians, and be used as a useful tool for mass classification.

Shift invariant extrema based feature analysis scheme to discriminate the spiculation nature of mammograms.

Since uncontrolled growth of malignant masses introduces uneven shape irregularities and spiculations in the boundary, shape representing shift invariant features are essential to resolve the problem of discrimination. However, ambiguous nature of shape, size, margin, orientation of masses produces imprecise feature values. In this view, a new concept of extrema based feature characterization scheme is proposed for capturing radiating nature of mass morphology. Computation of extrema patterns needs only few algorithmic steps. Beside this, present study employs an automated enhancement procedure to improve the classification accuracy. Experimental results show that extrema characterization reduces the feature redundancy to produce high efficiency in reasonably low time.

Evaluation of tumor shape features for overall survival prognosis in glioblastoma multiforme patients.

Glioblastoma multiforme (GBM) is a rapidly growing tumor associated with poor prognosis. This study evaluates the effectiveness of thirteen tumor shape features for overall survival (OS) prognosis in GBM patients. Shape features were extracted from the abnormality regions of the GBM tumor visible on the fluid attenuated inversion recovery (FLAIR) and T1-weighted contrast enhanced (T1CE) MR images of GBM patients. Survival analysis was performed using univariate and multivariate (with clinical features) Cox proportional hazards regression analysis. Kaplan-Meier survival curves were plotted and observed for the shape features which were found to be significant from the Cox regression analysis. Three 3D shape features: Bounding ellipsoid volume ratio (BEVR), sphericity and spherical disproportion, computed from both the abnormality regions were found to be significant for OS prognosis in GBM patients.

V4 shape features for contour representation and object detection.

Cortical area V4 lies in the middle of the visual pathway involved with object recognition. Neurons in V4 selectively respond to different curve fragments along the object contour. In this paper, we propose a computational model that captures the shape features extracted by V4 neurons. The computational model emulated the information processing mechanism in the visual cortex. It extracted curve segments that V4 neurons respond to and quantitatively represented features of the curve segments. The proposed V4 shape features could describe object contours accurately and efficiently. With quantitative evaluation using the MPEG7 shape dataset, we showed that complex shapes could be represented with a very limited number of V4 shape features. Based on V4 features, we further developed a self-organizing map neural network to learn object shape models. The shape model was defined by a group of V4 features with constraints on their spatial relationships. The model was evaluated in object detection experiments using ETHZ objects and INRIA horses datasets. The proposed model could learn to recognize objects by shapes and accurately outline the object contour in the images. Thus, this model provides insight into the neural mechanisms of shape-based object recognition.

Automated pterygium detection method of anterior segment photographed images.

BACKGROUND AND BJECTIVE: Pterygium is an ocular disease caused by fibrovascular tissue encroachment onto the corneal region. The tissue may cause vision blurring if it grows into the pupil region. In this study, we propose an automatic detection method to differentiate pterygium from non-pterygium (normal) cases on the basis of frontal eye photographed images, also known as anterior segment photographed images. METHODS: The pterygium screening system was tested on two normal eye databases (UBIRIS and MILES) and two pterygium databases (Australia Pterygium and Brazil Pterygium). This system comprises four modules: (i) a preprocessing module to enhance the pterygium tissue using HSV-Sigmoid; (ii) a segmentation module to differentiate the corneal region and the pterygium tissue; (iii) a feature extraction module to extract corneal features using circularity ratio, Haralick's circularity, eccentricity, and solidity; and (iv) a classification module to identify the presence or absence of pterygium. System performance was evaluated using support vector machine (SVM) and artificial neural network. RESULTS: The three-step frame differencing technique was introduced in the corneal segmentation module. The output image successfully covered the region of interest with an average accuracy of 0.9127. The performance of the proposed system using SVM provided the most promising results of 88.7%, 88.3%, and 95.6% for sensitivity, specificity, and area under the curve, respectively. CONCLUSION: A basic platform for computer-aided pterygium screening was successfully developed using the proposed modules. The proposed system can classify pterygium and non-pterygium cases reasonably well. In our future work, a standard grading system will be developed to identify the severity of pterygium cases. This system is expected to increase the awareness of communities in rural areas on pterygium.

[Effects of urban wetlands with different shapes on the temperature and humidity of ambient environment.] / 不同形状城市湿地对周边环境温湿度的影响.

To quantify the effects of urban wetlands on temperature and humidity of ambient environment, five urban wetlands with different shapes and surroundings were selected in Daqing City, and the air temperature and relative humidity were investigated in spring, summer and autumn using small-scale quantitative measurement method. The results indicated that the urban wetlands with different shapes all could decrease the temperature and increase the humidity, with the effect being strongest in summer, followed by in spring, and the smallest effect in autumn. The shape of the urban wetland had significant effect on temperature and humidity, which decreased in the order of irregular-shaped wetland > regular-shaped wetland (subcircular-shaped wetland, subcuboid-shaped wetland) > long-shaped wetland. The diurnal variation of temperature and humidity was influenced by the ambient temperature, namely the effect of wetlands was weak in morning and evening, but strong at noon. The maximum effect occurred at12:00-14:00 in spring and autumn, and at 14:00-16:00 in summer.

A novel retina-based human identification algorithm based on geometrical shape features using a hierarchical matching structure.

BACKGROUND AND OBJECTIVES: Retinal image is one of the most secure biometrics which is widely used in human identification application. This paper represents a rotation and translation-invariant human identification algorithm based on a new definition of geometrical shape features of the retinal image using a hierarchical matching structure. METHODS: In this algorithm, the retinal images are represented by regions which are surrounded by blood vessels that are named Surrounded Regions (SRs). A perfect set of region-based and boundary-based features are defined on the SRs. In the boundary-based features, by defining corner points of the SR, novel features such as angle of SR corner, centroid distance and weighted corner angle are defined which they can describe well the variation rate of boundary and geometry of the SR. To match the SR of a query with enrolled SR in database, the extracted features in a hierarchical structure from simpler features through more complex features are applied to filter the enrolled SRs in the database for search space reduction. At last, the matched candidate SRs with the query SRs determine the identification or rejection of query image by proposed decision making scenario. In this scenario, the identification is carried out when at least two SRs of the query are matched with two SRs of an individual in the database. RESULTS: The proposed algorithm is evaluated on STARE and DRIVE retinal image databases in six different experiments and is achieved an accuracy rate of 100% and an average processing time of 3.216sec and 3.225sec, respectively. The reported results demonstrate the efficiency of our proposed algorithm in the eye-movement condition. CONCLUSION: In our work, by defining the SR-based features and employing a hierarchical matching structure, the computational complexity of matching step is reduced and also the identification performance is improved. Moreover, the proposed algorithm overcomes the problem of natural movements of the head and eye during the capturing process.

Three-dimensional lung nodule segmentation and shape variance analysis to detect lung cancer with reduced false positives.

The three-dimensional analysis on lung computed tomography scan was carried out in this study to detect the malignant lung nodules. An automatic three-dimensional segmentation algorithm proposed here efficiently segmented the tissue clusters (nodules) inside the lung. However, an automatic morphological region-grow segmentation algorithm that was implemented to segment the well-circumscribed nodules present inside the lung did not segment the juxta-pleural nodule present on the inner surface of wall of the lung. A novel edge bridge and fill technique is proposed in this article to segment the juxta-pleural and pleural-tail nodules accurately. The centroid shift of each candidate nodule was computed. The nodules with more centroid shift in the consecutive slices were eliminated since malignant nodule's resultant position did not usually deviate. The three-dimensional shape variation and edge sharp analyses were performed to reduce the false positives and to classify the malignant nodules. The change in area and equivalent diameter was more for malignant nodules in the consecutive slices and the malignant nodules showed a sharp edge. Segmentation was followed by three-dimensional centroid, shape and edge analysis which was carried out on a lung computed tomography database of 20 patient with 25 malignant nodules. The algorithms proposed in this article precisely detected 22 malignant nodules and failed to detect 3 with a sensitivity of 88%. Furthermore, this algorithm correctly eliminated 216 tissue clusters that were initially segmented as nodules; however, 41 non-malignant tissue clusters were detected as malignant nodules. Therefore, the false positive of this algorithm was 2.05 per patient.

Statistical process control using optimized neural networks: a case study.

The most common statistical process control (SPC) tools employed for monitoring process changes are control charts. A control chart demonstrates that the process has altered by generating an out-of-control signal. This study investigates the design of an accurate system for the control chart patterns (CCPs) recognition in two aspects. First, an efficient system is introduced that includes two main modules: feature extraction module and classifier module. In the feature extraction module, a proper set of shape features and statistical feature are proposed as the efficient characteristics of the patterns. In the classifier module, several neural networks, such as multilayer perceptron, probabilistic neural network and radial basis function are investigated. Based on an experimental study, the best classifier is chosen in order to recognize the CCPs. Second, a hybrid heuristic recognition system is introduced based on cuckoo optimization algorithm (COA) algorithm to improve the generalization performance of the classifier. The simulation results show that the proposed algorithm has high recognition accuracy.