Surface detection of small defects plays a vital role in manufacturing and has attracted broad interest. It remains challenging primarily due to the small size of the defect relative to the large surface and the rare occurrence of defects. To address this problem, in this article we propose a novel machine vision approach for automatically identifying the tiny flaws that may appear in a single image. First, the presented defect exaggeration approach produces both the flawless image and the corresponding exaggerated version of the defect by taking the variations in the image as regularization terms. Second, a generative adversarial network (GAN) in conjunction with a convolutional neural network (CNN) is proposed to guarantee the accuracy of tiny surface defect detection by producing exaggerated defect image samples. Furthermore, the limited dataset of the training samples for defect detection is enlarged by exploiting the GAN technique with the variation exaggerated images. To evaluate the performance of our proposed method, we conduct comparison experiments between the state-of-the-art techniques with and without the proposed algorithm as well as comparison experiments between the state-of-the-art techniques and our method. The experimental results on different types of surface image samples demonstrate that the proposed method can significantly improve the performance of the state-of-the-art approaches while achieving a defect detection accuracy of 99.2%.

Determining banana’s ripening stages is becoming an essential requirement for standardizing the quality of commercial bananas. In this paper, we propose a novel convolutional neural network architecture which is designed specifically for the fine-grained classification of banana’s ripening stages. It learns a set of fine-grained image features based on a data-driven mechanism and offers a deep indicator of banana’s ripening stage. The resulted indicator can help to differentiate the subtle differences among subordinate classes of bananas in ripening state. Experimental results from 17,312 images of bananas in different ripening stages show that our deep indicator achieves an accuracy superior significantly to state-of-the-art computer vision-based systems both in rough- and fine-grained classification of ripening stages no matter the bananas bear or not severe defects.

In order to realize the recognition and localization of the target fruit more accurately and efficiently, an optimized graph-based recognition algorithm based on image depth information is proposed. Firstly, the gradient information of the depth image is obtained from the acquired depth apple image, the gradient vector is reflected from the 3D space to the 2D space, and then rotated 90 degrees clockwise, and the regular region forms the center of the vortex, which is the target fruit center to determine target fruit location. In the RGB space, the graph-based segmentation algorithm is introduced. By constructing the adaptive threshold, the mapping relationship between the number of centers and the parameters of k and min is established to find the target fruit region. Finally, scan the maximum radius of the super pixel area where the center of the circle is located, and fit the target fruit to realize the recognition and localization of the apple. The experimental results show that the target recognition rate is 96.61%, and the recognition time has been reduced significantly.

Introduction: The precise identification of retinal disorders is of utmost importance in the prevention of both temporary and permanent visual impairment. Prior research has yielded encouraging results in the classification of retinal images pertaining to a specific retinal condition. In clinical practice, it is not uncommon for a single patient to present with multiple retinal disorders concurrently. Hence, the task of classifying retinal images into multiple labels remains a significant obstacle for existing methodologies, but its successful accomplishment would yield valuable insights into a diverse array of situations simultaneously.Methods: This study presents a novel vision transformer architecture called retinal ViT, which incorporates the self-attention mechanism into the field of medical image analysis. To note that this study supposed to prove that the transformer-based models can achieve competitive performance comparing with the CNN-based models, hence the convolutional modules have been eliminated from the proposed model. The suggested model concludes with a multi-label classifier that utilizes a feed-forward network architecture. This classifier consists of two layers and employs a sigmoid activation function.Results and discussion: The experimental findings provide evidence of the improved performance exhibited by the suggested model when compared to state-of-the-art approaches such as ResNet, VGG, DenseNet, and MobileNet, on the publicly available dataset ODIR-2019, and the proposed approach has outperformed the state-of-the-art algorithms in terms of Kappa, F1 score, AUC, and AVG.

This paper presents a supervised feature learning method to learn discriminative and compact descriptors for drusen segmentation from retinal images. This method combines generalized low rank approximation of matrices with supervised manifold regularization to learn new features from image patches sampled from retinal images. The learned features are closely related to drusen and potentially free from information that is redundant in distinguishing drusen from background. The learned feature representations are then vectorized and used to train a support vector machine (SVM) classifier. Finally, the obtained SVM classifier is employed to classify the pixels in the test images as drusen or non-drusen. The performance of the proposed method is validated on the STARE and DRIVE databases, where it achieves an average sensitivity/specificity/accuracy of 90.03%/97.06%/96.92% and of 87.41%/94.93%/94.81%, respectively. We also experimentally compare the proposed method with the several representative state-of-the-art drusen segmentation techniques and find that it generates superior accuracy.

Multispectral imaging (MSI) provides a sequence of en-face fundus spectral slices and allows for the examination of structures and signatures throughout the thickness of retina to characterize diabetic retinopathy (DR) lesions comprehensively. Manual interpretation of MSI images is commonly conducted by qualitatively analyzing both the spatial and spectral properties of multiple spectral slices. Meanwhile, there exist few computer-based algorithms that can effectively exploit the spatial and spectral information of MSI images for the diagnosis of DR. We propose a new approach that can quantify the spatial-spectral features of MSI retinal images for automatic DR lesion segmentation. It combines a generalized low-rank approximation of matrices with a supervised regularization term to generate low-dimensional spatial-spectral representations using the feature vectors in all spectral slices. Experimental results showed that the proposed approach is very effective for the segmentation of DR lesions in MSI images, which suggests it as an interesting tool for assisting ophthalmologists in diagnosing, analyzing, and managing DR lesions in MSI.