Journal ArticleDOI
A comprehensive and systematic review on classical and deep learning based region proposal algorithms
Reads0
Chats0
TLDR
More than 60 different region proposal algorithms have been studied and classified as mentioned in this paper, including hand-crafted features and deep learning-based methods. But, most of these algorithms were based on a set of hand-crafted features.Abstract:
Development and improvement of region proposal algorithms have rapidly become one of the most critical research areas over recent years. The perfect accuracy of region-based recognition techniques has led to the use of proposal algorithms as an imperative core in various recognition problems. The main purpose of these algorithms is to extract effective regions of an image with an appropriate number that will reduce the search space and increase detection accuracy. The early development of these algorithms was based on a set of hand-crafted features. Recently, with advances in deep learning techniques, they have been widely and successfully applied to the region proposals. This paper reviews region proposal algorithms, theory, and evaluation metrics and also addresses the existing challenges. In addition, we present a classification for generating proposals, including classical and advanced methods based on hand-crafted features and deep learning, respectively. Both categories are described in details, and an extensive review of recent works is presented. The proposal improvement methods, including ranking algorithms, are also described. In total, more than 60 different algorithms have been studied and classified, and we also point out several applications based on region proposals.read more
Citations
More filters
Journal ArticleDOI
Chimp Optimization Algorithm to Optimize a Convolutional Neural Network for Recognizing Persian/Arabic Handwritten Words
Sara Khosravi,Abdolah Chalechale +1 more
TL;DR: A well-known nature-inspired technique called chimp optimization algorithm (ChOA) is applied to train a classical CNN structure LeNet-5 for Persian/Arabic handwritten recognition and indicates that the proposed ChOA technique considerably improves the performance of the original LeNet model and also shows a better performance than the others.
Journal ArticleDOI
Denoising and segmentation of brain image by proficient blended threshold and conserve edge scrutinize technique
TL;DR: In this paper , the authors have proposed an efficient image processing techniques by processing the MRI images of human brain which is affected by brain tumor using the proficient blended thresholding (PBT) Segmentation method.
Journal ArticleDOI
Multi-Object Tracking in Heterogeneous environments (MOTHe) for animal video recordings
TL;DR: MOTHe as mentioned in this paper is a Python-based application that uses a basic convolutional neural network for object detection and tracking in Heterogeneous environments, which can detect and track individuals in all these videos.
Journal ArticleDOI
Recognition of Persian/Arabic Handwritten Words Using a Combination of Convolutional Neural Networks and Autoencoder (AECNN)
Sara Khosravi,Abdolah Chalechale +1 more
TL;DR: In this paper , the authors proposed a new subword fusion algorithm based on the similarity of the main subwords and signs to enhance the recognition accuracy of Persian and Arabic manuscripts. But, the proposed approach is still a challenging problem due to complicated and irregular nature of writing, wide vocabulary, and diversity of handwritings.
Proceedings ArticleDOI
Semantic Segmentation Using Region Proposals and Weakly-Supervised Learning
TL;DR: In this article , a region proposal algorithm is used to convert an image into several regions, according to defined rules, regions are explored, and some precise regions are selected, and these masks are fed to a deep semantic segmentation network.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
Proceedings ArticleDOI
ImageNet: A large-scale hierarchical image database
TL;DR: A new database called “ImageNet” is introduced, a large-scale ontology of images built upon the backbone of the WordNet structure, much larger in scale and diversity and much more accurate than the current image datasets.
Book ChapterDOI
U-Net: Convolutional Networks for Biomedical Image Segmentation
TL;DR: Neber et al. as discussed by the authors proposed a network and training strategy that relies on the strong use of data augmentation to use the available annotated samples more efficiently, which can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.