RESUMEN
In vivo diseases such as colorectal cancer and gastric cancer are increasingly occurring in humans. These are two of the most common types of cancer that cause death worldwide. Therefore, the early detection and treatment of these types of cancer are crucial for saving lives. With the advances in technology and image processing techniques, computer-aided diagnosis (CAD) systems have been developed and applied in several medical systems to assist doctors in diagnosing diseases using imaging technology. In this study, we propose a CAD method to preclassify the in vivo endoscopic images into negative (images without evidence of a disease) and positive (images that possibly include pathological sites such as a polyp or suspected regions including complex vascular information) cases. The goal of our study is to assist doctors to focus on the positive frames of endoscopic sequence rather than the negative frames. Consequently, we can help in enhancing the performance and mitigating the efforts of doctors in the diagnosis procedure. Although previous studies were conducted to solve this problem, they were mostly based on a single classification model, thus limiting the classification performance. Thus, we propose the use of multiple classification models based on ensemble learning techniques to enhance the performance of pathological site classification. Through experiments with an open database, we confirmed that the ensemble of multiple deep learning-based models with different network architectures is more efficient for enhancing the performance of pathological site classification using a CAD system as compared to the state-of-the-art methods.
Asunto(s)
Neoplasias Colorrectales/diagnóstico por imagen , Aprendizaje Profundo , Diagnóstico por Computador , Procesamiento de Imagen Asistido por Computador , Neoplasias Gástricas/diagnóstico por imagen , Bases de Datos Factuales , Endoscopía , HumanosRESUMEN
Deep learning-based marker detection for autonomous drone landing is widely studied, due to its superior detection performance. However, no study was reported to address non-uniform motion-blurred input images, and most of the previous handcrafted and deep learning-based methods failed to operate with these challenging inputs. To solve this problem, we propose a deep learning-based marker detection method for autonomous drone landing, by (1) introducing a two-phase framework of deblurring and object detection, by adopting a slimmed version of deblur generative adversarial network (DeblurGAN) model and a You only look once version 2 (YOLOv2) detector, respectively, and (2) considering the balance between the processing time and accuracy of the system. To this end, we propose a channel-pruning framework for slimming the DeblurGAN model called SlimDeblurGAN, without significant accuracy degradation. The experimental results on the two datasets showed that our proposed method exhibited higher performance and greater robustness than the previous methods, in both deburring and marker detection.
RESUMEN
Although face-based biometric recognition systems have been widely used in many applications, this type of recognition method is still vulnerable to presentation attacks, which use fake samples to deceive the recognition system. To overcome this problem, presentation attack detection (PAD) methods for face recognition systems (face-PAD), which aim to classify real and presentation attack face images before performing a recognition task, have been developed. However, the performance of PAD systems is limited and biased due to the lack of presentation attack images for training PAD systems. In this paper, we propose a method for artificially generating presentation attack face images by learning the characteristics of real and presentation attack images using a few captured images. As a result, our proposed method helps save time in collecting presentation attack samples for training PAD systems and possibly enhance the performance of PAD systems. Our study is the first attempt to generate PA face images for PAD system based on CycleGAN network, a deep-learning-based framework for image generation. In addition, we propose a new measurement method to evaluate the quality of generated PA images based on a face-PAD system. Through experiments with two public datasets (CASIA and Replay-mobile), we show that the generated face images can capture the characteristics of presentation attack images, making them usable as captured presentation attack samples for PAD system training.
Asunto(s)
Identificación Biométrica/tendencias , Seguridad Computacional/tendencias , Reconocimiento Facial , Procesamiento de Imagen Asistido por Computador , Algoritmos , Cara , Humanos , Redes Neurales de la ComputaciónRESUMEN
Computer-aided diagnosis systems have been developed to assist doctors in diagnosing thyroid nodules to reduce errors made by traditional diagnosis methods, which are mainly based on the experiences of doctors. Therefore, the performance of such systems plays an important role in enhancing the quality of a diagnosing task. Although there have been the state-of-the art studies regarding this problem, which are based on handcrafted features, deep features, or the combination of the two, their performances are still limited. To overcome these problems, we propose an ultrasound image-based diagnosis of the malignant thyroid nodule method using artificial intelligence based on the analysis in both spatial and frequency domains. Additionally, we propose the use of weighted binary cross-entropy loss function for the training of deep convolutional neural networks to reduce the effects of unbalanced training samples of the target classes in the training data. Through our experiments with a popular open dataset, namely the thyroid digital image database (TDID), we confirm the superiority of our method compared to the state-of-the-art methods.
Asunto(s)
Inteligencia Artificial , Neoplasias de la Tiroides/diagnóstico , Nódulo Tiroideo/diagnóstico , Ultrasonografía/métodos , Biopsia con Aguja Fina/métodos , Diagnóstico por Computador/métodos , Humanos , Interpretación de Imagen Asistida por Computador/métodos , Redes Neurales de la Computación , Glándula Tiroides/diagnóstico por imagen , Glándula Tiroides/patología , Neoplasias de la Tiroides/diagnóstico por imagen , Neoplasias de la Tiroides/patología , Nódulo Tiroideo/diagnóstico por imagen , Nódulo Tiroideo/patologíaRESUMEN
Image-based computer-aided diagnosis (CAD) systems have been developed to assist doctors in the diagnosis of thyroid cancer using ultrasound thyroid images. However, the performance of these systems is strongly dependent on the selection of detection and classification methods. Although there are previous researches on this topic, there is still room for enhancement of the classification accuracy of the existing methods. To address this issue, we propose an artificial intelligence-based method for enhancing the performance of the thyroid nodule classification system. Thus, we extract image features from ultrasound thyroid images in two domains: spatial domain based on deep learning, and frequency domain based on Fast Fourier transform (FFT). Using the extracted features, we perform a cascade classifier scheme for classifying the input thyroid images into either benign (negative) or malign (positive) cases. Through expensive experiments using a public dataset, the thyroid digital image database (TDID) dataset, we show that our proposed method outperforms the state-of-the-art methods and produces up-to-date classification results for the thyroid nodule classification problem.
RESUMEN
A paradigm shift is required to prevent the increasing automobile accident deaths that are mostly due to the inattentive behavior of drivers. Knowledge of gaze region can provide valuable information regarding a driver's point of attention. Accurate and inexpensive gaze classification systems in cars can improve safe driving. However, monitoring real-time driving behaviors and conditions presents some challenges: dizziness due to long drives, extreme lighting variations, glasses reflections, and occlusions. Past studies on gaze detection in cars have been chiefly based on head movements. The margin of error in gaze detection increases when drivers gaze at objects by moving their eyes without moving their heads. To solve this problem, a pupil center corneal reflection (PCCR)-based method has been considered. However, the error of accurately detecting the pupil center and corneal reflection center is increased in a car environment due to various environment light changes, reflections on glasses surface, and motion and optical blurring of captured eye image. In addition, existing PCCR-based methods require initial user calibration, which is difficult to perform in a car environment. To address this issue, we propose a deep learning-based gaze detection method using a near-infrared (NIR) camera sensor considering driver head and eye movement that does not require any initial user calibration. The proposed system is evaluated on our self-constructed database as well as on open Columbia gaze dataset (CAVE-DB). The proposed method demonstrated greater accuracy than the previous gaze classification methods.
Asunto(s)
Aprendizaje Automático , Conducción de Automóvil , Automóviles , Movimientos Oculares , Fijación Ocular , Movimientos de la Cabeza , HumanosRESUMEN
Intelligent surveillance systems have been studied by many researchers. These systems should be operated in both daytime and nighttime, but objects are invisible in images captured by visible light camera during the night. Therefore, near infrared (NIR) cameras, thermal cameras (based on medium-wavelength infrared (MWIR), and long-wavelength infrared (LWIR) light) have been considered for usage during the nighttime as an alternative. Due to the usage during both daytime and nighttime, and the limitation of requiring an additional NIR illuminator (which should illuminate a wide area over a great distance) for NIR cameras during the nighttime, a dual system of visible light and thermal cameras is used in our research, and we propose a new behavior recognition in intelligent surveillance environments. Twelve datasets were compiled by collecting data in various environments, and they were used to obtain experimental results. The recognition accuracy of our method was found to be 97.6%, thereby confirming the ability of our method to outperform previous methods.
RESUMEN
Recently, human detection has been used in various applications. Although visible light cameras are usually employed for this purpose, human detection based on visible light cameras has limitations due to darkness, shadows, sunlight, etc. An approach using a thermal (far infrared light) camera has been studied as an alternative for human detection, however, the performance of human detection by thermal cameras is degraded in case of low temperature differences between humans and background. To overcome these drawbacks, we propose a new method for human detection by using thermal camera images. The main contribution of our research is that the thresholds for creating the binarized difference image between the input and background (reference) images can be adaptively determined based on fuzzy systems by using the information derived from the background image and difference values between background and input image. By using our method, human area can be correctly detected irrespective of the various conditions of input and background (reference) images. For the performance evaluation of the proposed method, experiments were performed with the 15 datasets captured under different weather and light conditions. In addition, the experiments with an open database were also performed. The experimental results confirm that the proposed method can robustly detect human shapes in various environments.