Livestock detection in aerial images using a fully convolutional network

Computational Visual Media - In order to accurately count the number of animals grazing on grassland, we present a livestock detection algorithm using modified versions of U-net and Google...     

Evidential fully convolutional network for semantic segmentation

Applied Intelligence - We propose a hybrid architecture composed of a fully convolutional network (FCN) and a Dempster-Shafer layer for image semantic segmentation. In the so-called evidential FCN...     

C-FCN: Corners-based fully convolutional network for visual object detection

Object detection has achieved significantly progresses in recent years. Proposal-based methods have become the mainstream object detectors, achieving excellent performance on accurate recognition and localization of objects. However, region proposal generation is still a bottleneck. In this paper, to address the limitations of conventional region proposal network (RPN) that defines dense anchor boxes with different scales and aspect ratios, we propose an anchor-free proposal generator named corner region proposal network (CRPN) which is based on a pair of key-points, including top-left corner and bottom-right corner of an object bounding box. First, we respectively predict the top-left corners and bottom-right corners by two sibling convolutional layers, then we obtain a set of object proposals by grouping strategy and non-maximum suppression algorithm. Finally, we further merge CRPN and fully convolutional network (FCN) into a unified network, achieving an end-to-end object detection. Our method has been evaluated on standard PASCAL VOC and MS COCO datasets using a deep residual network. Experiment results present that the proposed method outperforms previous detectors in the term of precision. Additionally, it runs with a speed of 76 ms per image on a single GPU by using ResNet-50 as the backbone, which is faster than other detectors.

     

基于HarDNet全卷积网络的道路路面语义分割方法

道路路面可行驶区域识别是无人驾驶环境感知的重要组成部分.针对计算资源有限的车载设备,设计了基于HarDNet全卷积网络的道路路面语义分割方法.首先,在U-Net语义分割框架中使用低内存消耗的HarDNet卷积神经网络结构提取卷积特征进行路面分割;其次,在模型训练时对图像标签进行权重增强,提升路面边缘分割精度;然后,针对国内道路特点,构建国内道路路面分割数据集;最后,使用基于像素的交叉熵函数和Softmax的损失函数,结合平移、形变、填充、灰度处理、"复制粘贴"的数据增强方法进行模型训练.在构造的国内道路数据集上进行算法测试,实验结果表明所提方法的平均交并比值为94.5,在AGX Xavier设备上运行速度为10.6帧/秒.在满足无人车计算力要求的前提下,尽可能提升了路面可行驶区域分割的精度.     

A simple and effective table detection system from document images

The requirement of detection and identification of tables from document images is crucial to any document image analysis and digital library system. In this paper we report a very simple but extremely powerful approach to detect tables present in document pages. The algorithm relies on the observation that the tables have distinct columns which implies that gaps between the fields are substantially larger than the gaps between the words in text lines. This deceptively simple observation has led to the design of a simple but powerful table detection system with low computation cost. Moreover, mathematical foundation of the approach is also established including formation of a regular expression for ease of implementation.     

Gland segmentation in colorectal cancer histopathological images using U-net inspired convolutional network

Neural Computing and Applications - The accurate gland segmentation from digitized H&E (hematoxylin and eosin) histology images with a wide range of histologic grades of cancer is quite...     

A convolutional neural network model for semantic segmentation of mitotic events in microscopy images

Neural Computing and Applications - Mitosis, which has important effects such as healing and growing for human body, has attracted considerable attention in recent years. Especially, cell division...     

Multi-atlas segmentation of optic disc in retinal images via convolutional neural network

Multi-atlas segmentation is widely accepted as an essential image segmentation approach. Through leveraging on the information from the atlases instead of utilizing the model-based segmentation techniques, the multi-atlas segmentation could significantly enhance the accuracy of segmentation. However, label fusion, which plays an important role for multi-atlas segmentation still remains the primary challenge. Bearing this in mind, a deep learning-based approach is presented through integrating feature extraction and label fusion. The proposed deep learning architecture consists of two independent channels composing of continuous convolutional layers. To evaluate the performance our approach, we conducted comparison experiments between state-of-the-art techniques and the proposed approach on publicly available datasets. Experimental results demonstrate that the accuracy of the proposed approach outperforms state-of-the-art techniques both in efficiency and effectiveness.

     

Cell detection in pathology and microscopy images with multi-scale fully convolutional neural networks

Automated nucleus/cell detection is usually considered as the basis and a critical prerequisite step of computer assisted pathology and microscopy image analysis. However, due to the enormous variability (cell types, stains and different microscopes) and data complexity (cell overlapping, inhomogeneous intensities, background clutters and image artifacts), robust and accurate nucleus/cell detection is usually a difficult problem. To address this issue, we propose a novel multi-scale fully convolutional neural networks approach for regression of a density map to robustly detect the nuclei of pathology and microscopy images. The procedure can be divided into three main stages. Initially, instead of working on the simple dot label space, regression on the proposed structured proximity space for patches is performed so that centers of image patches are explicitly forced to produce larger values than their adjacent areas. Then, several multi-scale fully convolutional regression networks are developed for this task; this will enlarge the receptive field and not only can detect the single, small size cells, but also benefit to detecting cells with big size and overlapping states. In this stage, we copy the full feature maps from the contracting path and merge with the feature maps of the expansive path. This operation will make full use of shallow and deep semantic information of the networks. The networks do not have any fully connected layers; this strategy allows the seamless probability map prediction of arbitrarily large images. At the same time, data augmentations (e.g., small range shift, zoom and randomly flip) are carefully used to enhance the robustness of detection. Finally, morphological operations and suitable filters are employed and some prior information is introduced to find the centers of the cells more robustly. Our method achieves about 99.25% detection precision and the F1-measure is 0.9924 on fluorescence microscopy cell images; about 85.90% detection precision and the F1-measure is 0.9020 on Lymphocyte cell images and about 78.41% detection precision and the F1-measure is 0.8440 on breast histopathological images. This result leads to a promising detection performance that equates and sometimes exceeds the recently published leading detection approaches with the same benchmark datasets.     

Computer-aided retinal vessel segmentation in retinal images: convolutional neural networks

In medicine, diagnosis is as important as treatment. Retinal blood vessels are the most easily visible vessels in the whole body, and therefore, play a key role in the diagnosis of numerous diseases and eye disorders. Systematic and eye diseases cause morphologic variations, such as the growing, narrowing or branching of retinal blood vessels. Imaging-based screening of retinal blood vessels plays an important role in the identification and follow-up of eye diseases. Therefore, automatic retinal vessel segmentation can be used to diagnose and monitor those diseases. Computer-aided algorithms are required for the analysis of progression of eye diseases. This study proposes a hybrid method that provides a combination of pre-processing and data augmentation methods with a deep learning model. Pre-processing was used to solve the irregular clarification problems and to form a contrast between the background and retinal blood vessels. After pre-processing step, a convolutional neural network (CNN) was designed and then trained for the extraction of retinal blood vessels. In the training phase, data augmentation was performed to improve training performance. The CNN was trained and tested in the DRIVE database, which is commonly used in retinal blood vessel segmentation and publicly available for studies in this area. Results showed that the proposed system extracted vessels with a sensitivity of 77.78%, specificity of 97,84%, precision of 84.17% and accuracy of 95.27%.

This study also compared the results to those of previous studies. The comparison showed that the proposed method is an efficient and successful method for extracting retinal blood vessels. Moreover, the pre-processing phases improved the system performance. We believe that the proposed method and results will make contribution to the literature.

     

Bottom-up improved multistage temporal convolutional network for action segmentation

Applied Intelligence - Action segmentation involves locating and classifying human action segments in an untrimmed video, which is very important for understanding human activities. Segmenting...     

YOLO-table: disclosure document table detection with involution

As financial document automation becomes more general, table detection is receiving more and more attention as an important part of document automation. Disclosure documents contain both bordered and borderless tables of varying lengths, and there is currently no model that performs well on these types of documents. To solve this problem, we propose a table detection model based on YOLO-table. We introduce involution into the backbone of the network to improve the network’s ability to learn table spatial layout features and design a simple Feature Pyramid Network to improve model effectiveness. In addition, this paper proposes a table-based augment method. We experiment on a disclosure document dataset, and the results show that the F1-measure of the YOLO-table reaches 97.3%. Compared with YOLOv3, our method improves the accuracy by 2.8% and the speed by 1.25 times. It also evaluates the ICDAR2013 and ICDAR2019 Table Competition datasets and achieves state-of-the-art performance.

     

A multi-plane approach for text segmentation of complex document images

This study presents a new method, namely the multi-plane segmentation approach, for segmenting and extracting textual objects from various real-life complex document images. The proposed multi-plane segmentation approach first decomposes the document image into distinct object planes to extract and separate homogeneous objects including textual regions of interest, non-text objects such as graphics and pictures, and background textures. This process consists of two stages—localized histogram multilevel thresholding and multi-plane region matching and assembling. Then a text extraction procedure is applied on the resultant planes to detect and extract textual objects with different characteristics in the respective planes. The proposed approach processes document images regionally and adaptively according to their respective local features. Hence detailed characteristics of the extracted textual objects, particularly small characters with thin strokes, as well as gradational illuminations of characters, can be well-preserved. Moreover, this way also allows background objects with uneven, gradational, and sharp variations in contrast, illumination, and texture to be handled easily and well. Experimental results on real-life complex document images demonstrate that the proposed approach is effective in extracting textual objects with various illuminations, sizes, and font styles from various types of complex document images.     

Coupled snakelets for curled text-line segmentation from warped document images

Camera-captured, warped document images usually contain curled text-lines because of distortions caused by camera perspective view and page curl. Warped document images can be transformed into planar document images for improving optical character recognition accuracy and human readability using monocular dewarping techniques. Curled text-lines segmentation is a crucial initial step for most of the monocular dewarping techniques. Existing curled text-line segmentation approaches are sensitive to geometric and perspective distortions. In this paper, we introduce a novel curled text-line segmentation algorithm by adapting active contour (snake). Our algorithm performs text-line segmentation by estimating pairs of x-line and baseline. It estimates a local pair of x-line and baseline on each connected component by jointly tracing top and bottom points of neighboring connected components, and finally each group of overlapping pairs is considered as a segmented text-line. Our algorithm has achieved curled text-line segmentation accuracy of above 95% on the DFKI-I (CBDAR 2007 dewarping contest) dataset, which is significantly better than previously reported results on this dataset.     

N-FTRN: Neighborhoods based fully convolutional network for Chinese text line recognition

Multimedia Tools and Applications - The convolutional recurrent neural network is one of the most popular text recognition methods. Recurrent structures can extract long-term dependencies, but they...     

SpinNet: Spinning convolutional network for lane boundary detection

Computational Visual Media - In this paper, we propose a simple but effective framework for lane boundary detection, called SpinNet. Considering that cars or pedestrians often occlude lane...     

Recurrent convolutional network for video-based smoke detection

Multimedia Tools and Applications - Video-based smoke detection plays an important role in the fire detection community. Such interesting topic, however, always suffers from great challenge due to...     

Automatic breast tumor detection in ABVS images based on convolutional neural network and superpixel patterns

Breast cancer is one of the most common female malignancies, as well as the second leading cause of mortality for women. Early detection and treatment can dramatically decrease the mortality rate. Recently, automated breast volume scanner (ABVS) has become one of the most frequently used diagnose methods for breast tumor screening because of its operator-independent and reproducible advantages. However, it is a challenging job to obtain the tumors’ accurate locations and shapes by reviewing hundreds of ABVS slices. In this paper, a novel computer-aided detection (CADe) system is developed to reduce clinicians’ reading time and improve the efficiency. The CADe system mainly contains three parts: tumor candidate acquisition, false-positive reduction and tumor segmentation. Firstly, a local phase-based approach is built to obtain breast tumor candidates for further recognition. Subsequently, a convolutional neural network (CNN) is applied to reduce false positives (FPs). The introduction of CNN can help to avoid complicated feature extraction as well as elevate the accuracy and efficiency. Finally, superpixel-based segmentation is used to outline the breast tumor. Here, superpixel-based local binary pattern (SLBP) is proposed to assist the segmentation, which improves the performance. The methods were evaluated on a clinical ABVS dataset whose abnormal cases were manually labeled by an experienced radiologist. The experiment results were mainly composed of two parts. At the FP reduction stage, the proposed CNN achieved 100% and 78.12% sensitivity with FPs/case of 2.16 and 0. At the segmentation stage, our SLBP obtained 82.34% true positive, 15.79% false positive and 83.59% Dice similarity. In summary, the proposed CADe system demonstrated promising potential to detect and outline breast tumors in ABVS images.

     

Scene text detection with fully convolutional neural networks

Multimedia Tools and Applications - Text detection in scene image has become a hot topic in computer vision and artificial intelligence research, due to its wide range of applications and...