MaskDis R‐CNN: An instance segmentation algorithm with adversarial network for herd pigs

In this paper, an efficient instance segmentation scheme based on deep convolutional neural networks is proposed to deal with unconstrained psoriasis images for computer-aided diagnosis. To achieve instance segmentation, the You Only Look At CoefficienTs (YOLACT) network composed of backbone, feature pyramid network (FPN), Protonet, and prediction head is used to deal with psoriasis images. The backbone network is used to extract feature maps from an image, and FPN is designed to generate multiscale feature maps for effectively classifying and localizing objects with multiple sizes. The prediction head is used to predict the classification information, bounding box information, and mask coefficients of objects. Some prototypes generated by Protonet are combined with mask coefficients to estimate the pixel-level shapes for objects. To achieve instance segmentation for unconstrained psoriasis images, YOLACT++ with a pretrained model is retrained via transfer learning. To evaluate the performance of the proposed scheme, unconstrained psoriasis images with different severity levels are collected for testing. As for subjective testing, the psoriasis regions and normal skin areas can be located and classified well. The four performance indices of the proposed scheme were higher than 93% after cross validation. About object localization, the Mean Average Precision (mAP) rates of the proposed scheme were at least 85.9% after cross validation. As for efficiency, the frames per second (FPS) rate of the proposed scheme reached up to 15. In addition, the F1_score and the execution speed of the proposed scheme were higher than those of the Mask Region-Based Convolutional Neural Networks (R-CNN)-based method. These results show that the proposed scheme based on YOLACT++ can not only detect psoriasis regions but also distinguish psoriasis pixels from background and normal skin pixels well. Furthermore, the proposed instance segmentation scheme outperforms the Mask R-CNN-based method for unconstrained psoriasis images.

Detection of metastasis of mediastinal lymph nodes in lung cancer patients with an artificial intelligence model.

Melanoma lesion detection and segmentation using deep region based convolutional neural network and fuzzy C-means clustering

CAPTCHA (Completely Automated Public Turing test to tell Computers and Humans Apart) systems serve as a crucial defense mechanism against automated attacks by distinguishing between human users and bots. However, advancements in deep learning have posed significant challenges to the security of conventional CAPTCHA systems. In this research paper, we present a comparative analysis of two prominent object detection algorithms, Convolutional Neural Networks (CNN) and Region-based Convolutional Neural Networks (RCNN), for breaking CAPTCHAs. The study evaluates the performance of CNN and RCNN algorithms in accurately identifying and deciphering characters within CAPTCHA images. Utilizing a diverse dataset of CAPTCHA samples, experiments are conducted to assess the effectiveness of both algorithms in handling variations in CAPTCHA styles, languages, and complexities. Through extensive experimentation and evaluation, we analyze the strengths and limitations of CNN and RCNN in the context of CAPTCHA breaking. Key metrics such as accuracy, precision, recall, and computational efficiency are compared to provide insights into the relative performance of each algorithm. The findings of this research contribute to the understanding of object detection techniques for CAPTCHA breaking and provide valuable insights for enhancing the security of CAPTCHA systems against emerging threats posed by deep learning-based attacks.

Object segmentation and classification using the deep convolutional neural network (DCNN) has been widely researched in recent years. On the one hand, DCNN requires large data training sets and precise labeling, which bring about great difficulties in practical application. On the other hand, it consumes a large amount of computing resources, so it is difficult to apply it to low-cost terminal equipment. This paper proposes a method of crop organ segmentation and disease recognition that is based on weakly supervised DCNN and lightweight model. While considering the actual situation in the greenhouse, we adopt a two-step strategy to reduce the interference of complex background. Firstly, we use generic instance segmentation architecture—Mask R-CNN to realize the instance segmentation of tomato organs based on weakly supervised learning, and then the disease recognition of tomato leaves is realized by depth separable multi-scale convolution. Instance segmentation algorithms usually require accurate pixel-level supervised labels, which are difficult to collect, so we propose a weakly supervised instance segmentation assignment to solve this problem. The lightweight model uses multi-scale convolution to expand the network width, which makes the extracted features richer, and depth separable convolution is adopted to reduce model parameters. The experimental results showed that our method reached higher recognition accuracy when compared with other methods, at the same time occupied less memory space, which can realize the real-time recognition of tomato diseases on low-performance terminals, and can be applied to the recognition of crop diseases in other similar application scenarios.

In this paper, a new Region-based Convolutional Neural Networks (RCNN) method is proposed for target recognition in large scene synthetic aperture radar (SAR) images. To locate and recognize the targets in SAR images, there are three steps in the traditional procedure: detection, discrimination, classification and recognition. Each step is supposed to provide optimal processing results for the next step, but this is difficult to implement in real-life applications because of speckle noise and inefficient connection among these procedures. To solve this problem, the RCNN is applied to large scene SAR target recognition, which can detect the objects while recognizing their classes based on its regression method and the sharing network structure. However, size of the input images to RCNN is limited so that the classification could be accomplished, which leads to a problem that RCNN is not able to handle the large scene SAR images directly. Thus, before the RCNN, a fast sliding method is proposed to segment the scene image into sub-images with suitable size and avoid dividing targets into different sub-images. After the RCNN, candidate regions on different slices are predicted. To locate targets on large scene SAR images from these candidate regions on small slices, the Non-maximum Suppression between Regions (NMSR) is proposed, which could find the most proper candidate region among all the overlapped regions. Experiments on 1476 × 1784 simulated MSTAR images of simple scenes and complex scenes show that the proposed method can recognize all targets with the best accuracy and fastest speed, and outperform the other methods, such as constant false alarm rate (CFAR) detector + support vector machine (SVM), Visual Attention+SVM, and Sliding-RCNN.

Human gender detection from body profile is an important task for surveillance. Most surveillance cameras are placed at a distance such that it is not possible to see people's face clearly. In this paper, we report the comparison between fast-feature pyramids and deep region-based convolutional neural network (RCNN) to detect a person in surveillance images. Since RCNN performs better in detecting a person, further training is applied to the RCNN to detect man and woman. Transfer learning strategy is used due to a small number of training images. The result shows that the trained RCNN can detect man and woman with promising result.

Instance segmentation needs to locate all instances in an image correctly and segment each instance precisely. Currently, the most dominant methods for instance segmentation take object detection as a pre-task. However, they rely on the accuracy of object detection incredibly. If the pre-task cannot predict an accurate bounding box, the performance of instance segmentation will degenerate. In this paper, we present a novel method for instance segmentation to solve this problem, which is called <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">S</b> egmenting <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">B</b> eyond the <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">B</b> ounding <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">B</b> ox ( <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">S3B-Net</b> ). Our S3B-Net designs a sub-network to help instance segmentation methods based on object detection to segment the part of an instance beyond the bounding box. Specifically, the sub-network first predicts a two-dimensional pixel embedding for each pixel. Then, the Gaussian function is employed to calculate a pixel’s probability belongs to a corresponding instance according to the two-dimensional pixel embedding. Finally, the output of the sub-network combines with the output of instance segmentation based on object detection to generate a more precise instance mask. Our sub-network can easily extend on the existing instance segmentation method based on object detection to segment instance beyond the bounding box. We do our experiments on dominant instance segmentation datasets, such as the COCO dataset and Cityscapes dataset. The results show that our method can achieve 6.8 points gain compared with the baseline Mask R-CNN with ResNet-50-FPN in Cityscapes datasets, and 1.7 points gain with ResNet-101-FPN-DCN in COCO datasets. Our S3B-Net outperforms the previous state-of-the-art instance segmentation method, which proves our method is competitive. The source code of our method will be made available.

Instance Segmentation and Localization of Strawberries in Farm Conditions for Automatic Fruit Harvesting

In recent years, the integration of machine learning within the field of biological and medical sciences has significantly enhanced our ability to interpret complex clinical data. This advancement has been especially impactful in the domain of neurodegenerative disorders such as Parkinson’s Disease (PD), where early and precise diagnosis remains a persistent challenge. In this study, we propose a novel approach utilizing a Region-based Convolutional Neural Network (R-CNN) to distinguish between healthy individuals and those affected by PD. The method focuses on identifying subtle but meaningful patterns in visual diagnostic tools such as spiral and wave drawings, which are known to reflect motor impairments typical of the disease. Parkinson’s Disease is characterized by the progressive degeneration of motor control, often manifesting in tremors, rigidity, and bradykinesia. While traditional diagnostic techniques depend heavily on the observational skills of neurologists—assessing speech, writing, gait, and hand-drawn spirals—the process can be both time-consuming and subjective. To overcome these limitations, we adopted a deep learning strategy, using Faster R-CNN to directly analyze input patterns without manual feature extraction. This model automates the learning of distinguishing features from a dataset comprising MRI images and spiral drawing samples, enabling accurate classification with minimal human intervention. The system was trained and tested on real biomedical drawing datasets, including spiral and wave patterns from both PD patients and healthy controls. We achieved an accuracy of 96% during training and 86–97% during testing using batch normalization, which stabilized learning and minimized overfitting. This high performance clearly demonstrates the effectiveness of our approach in capturing the fine-grained motor distortions associated with Parkinson’s Disease. The model’s ability to learn from nuanced visual cues reflects its strength in identifying early-stage abnormalities, which are often difficult to detect with conventional tools. Moreover, this research highlights the superiority of the proposed model when compared to existing state-of-the-art methods. The results demonstrated not only robustness in pattern recognition but also the potential for real-world clinical applications. By automating a significant portion of the diagnostic workflow, this approach could reduce diagnostic delays and support neurologists in making more informed decisions. The system has proven effective in its current implementation and will be further validated using a broader, more diverse set of clinical data in future work. Keywords - Deep Learning - R-CNN - Spiral Drawing Analysis - Medical Image Classification - Early Diagnosis.

Semantic and instance segmentation algorithms are two general yet distinct image segmentation solutions powered by Convolution Neural Network. While semantic segmentation benefits extensively from the end-to-end training strategy, instance segmentation is frequently framed as a multi-stage task, supported by learning-based discrimination and post-process clustering. Independent optimizations on substages instigate the accumulation of segmentation errors. In this work, we propose to embed prior clustering information into an embedding learning framework FCRNet, stimulating the one-stage instance segmentation. FCRNet relieves the complexity of post process by incorporating the number of clustering groups into the embedding space. The superior performance of FCRNet is verified and compared with other methods on the nucleus dataset BBBC006.

Offshore and inland river ship detection has been studied on both synthetic aperture radar (SAR) and optical remote sensing imagery. However, the classic ship detection methods based on SAR images can cause a high false alarm ratio and be influenced by the sea surface model, especially on inland rivers and in offshore areas. The classic detection methods based on optical images do not perform well on small and gathering ships. This paper adopts the idea of deep networks and presents a fast regional-based convolutional neural network (R-CNN) method to detect ships from high-resolution remote sensing imagery. First, we choose GaoFen-2 optical remote sensing images with a resolution of 1 m and preprocess the images with a support vector machine (SVM) to divide the large detection area into small regions of interest (ROI) that may contain ships. Then, we apply ship detection algorithms based on a region-based convolutional neural network (R-CNN) on ROI images. To improve the detection result of small and gathering ships, we adopt an effective target detection framework, Faster-RCNN, and improve the structure of its original convolutional neural network (CNN), VGG16, by using multiresolution convolutional features and performing ROI pooling on a larger feature map in a region proposal network (RPN). Finally, we compare the most effective classic ship detection method, the deformable part model (DPM), another two widely used target detection frameworks, the single shot multibox detector (SSD) and YOLOv2, the original VGG16-based Faster-RCNN, and our improved Faster-RCNN. Experimental results show that our improved Faster-RCNN method achieves a higher recall and accuracy for small ships and gathering ships. Therefore, it provides a very effective method for offshore and inland river ship detection based on high-resolution remote sensing imagery.

Pathological myopia is a major cause of blindness among people under 50 years old and can result in severe vision loss in extreme cases. Currently, its detection primarily relies on manual methods, which are slow and heavily dependent on the expertise of physicians, making them impractical for large-scale screening. To tackle these challenges, we propose SMLS-YOLO, an instance segmentation method based on YOLOv8n-seg. Designed for efficiency in large-scale screenings, SMLS-YOLO employs an extremely lightweight model. First, StarNet is introduced as the backbone of SMLS-YOLO to extract image features. Subsequently, the StarBlock from StarNet is utilized to enhance the C2f, resulting in the creation of the C2f-Star feature extraction module. Furthermore, shared convolution and scale reduction strategies are employed to optimize the segmentation head for a more lightweight design. Lastly, the model incorporates the Multi-Head Self-Attention (MHSA) mechanism following the backbone to further refine the feature extraction process. Experimental results on the pathological myopia dataset demonstrate that SMLS-YOLO outperforms the baseline YOLOv8n-seg by reducing model parameters by 46.9%, increasing Box mAP@0.5 by 2.4%, and enhancing Mask mAP@0.5 by 4%. Furthermore, when compared to other advanced instance segmentation and semantic segmentation algorithms, SMLS-YOLO also maintains a leading position, suggesting that SMLS-YOLO has promising applications in the segmentation of pathological myopia images.

Plant diseases cause low agricultural productivity. Plant diseases are challenging to control and identify by the majority of farmers. In order to reduce future losses, early disease diagnosis is necessary. This study looks at how to identify tomato plant leaf disease using machine learning techniques, including the Fuzzy Support Vector Machine (Fuzzy-SVM), Convolution Neural Network (CNN), and Region-based Convolution Neural Network (R-CNN). The findings were confirmed using images of tomato leaves with six diseases and healthy samples. Image scaling, color thresholding, flood filling approaches for segmentation, gradient local ternary pattern, and Zernike moments’ features are used to train the pictures. R-CNN classifiers are used to classify the illness kind. The classification methods of Fuzzy SVM and CNN are analyzed and compared with R-CNN to determine the most accurate model for plant disease prediction. The R-CNN-based Classifier has the most remarkable accuracy of 96.735 percent compared to the other classification approaches.

Extracting building instances from remote sensing images has various applications. However, existing instance segmentation methods have difficulty maintaining regular and angular building boundaries, corrupting the mask quality. This letter proposes a boundary-optimized instance segmentation method based on the direction field to cope with the low boundary quality. The proposed method develops a DF-Mask head to improve the mask quality of the primary instance segmentation network (Mask R-CNN) through boundary optimization. Within the DF-Mask head, first, a gated directional context-aware module (GDCAM) improves the mask features through the directional context and a designed gating mechanism. Then a direction field rectification module (DFRM) predicts the direction field and iteratively rectifies the mask. To the best of our knowledge, this is the first time that direction field rectification has been developed to the instance segmentation method and applied to building instance extraction. Experimental results on the Vaihingen and Massachusetts datasets suggest that our method outperforms the eight state-of-the-art methods. Compared with Mask R-CNN, our method improves APs by 4.7% and 2.2% on the two datasets, respectively.