SqueezeVGGNet: A Methodology for designing low complexity VGG Architecture for Resource Constraint Edge Applications

Text recognition in natural scene images is a challenging problem in computer vision. Different than the optical character recognition (OCR), text recognition in natural scene images is more complex due to variations in text size, colors, fonts, orientations, complex backgrounds, occlusion, illuminations and uneven lighting conditions. In this paper, we propose a segmentation-free method based on a deep convolutional recurrent neural network to solve the problem of cursive text recognition, particularly focusing on Urdu text in natural scenes. Compared to the non-cursive scripts, Urdu text recognition is more complex due to variations in the writing styles, several shapes of the same character, connected text, ligature overlapping, stretched, diagonal and condensed text. The proposed model gets a whole word image as an input without pre-segmenting into individual characters, and then transforms into the sequence of the relevant features. Our model is based on three components: a deep convolutional neural network (CNN) with shortcut connections to extract and encode the features, a recurrent neural network (RNN) to decode the convolutional features, and a connectionist temporal classification (CTC) to map the predicted sequences into the target labels. To increase the text recognition accuracy further, we explore deeper CNN architectures like VGG-16, VGG-19, ResNet-18 and ResNet-34 to extract more appropriate Urdu text features, and compare the recognition results. To conduct the experiments, a new large-scale benchmark dataset of cropped Urdu word images in natural scenes is developed. The experimental results show that the proposed deep CRNN network with shortcut connections outperform than other network architectures. The dataset is publicly available and can be downloaded from <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://data.mendeley.com/datasets/k5fz57zd9z/1</uri> .

Image-based localization, or camera relocalization, is a fundamental problem in computer vision and robotics, and it refers to estimating camera pose from an image. Recent state-of-the-art approaches use learning based methods, such as Random Forests (RFs) and Convolutional Neural Networks (CNNs), to regress for each pixel in the image its corresponding position in the scene's world coordinate frame, and solve the final pose via a RANSAC-based optimization scheme using the predicted correspondences. In this paper, instead of in a patch-based manner, we propose to perform the scene coordinate regression in a full-frame manner to make the computation efficient at test time and, more importantly, to add more global context to the regression process to improve the robustness. To do so, we adopt a fully convolutional encoder-decoder neural network architecture which accepts a whole image as input and produces scene coordinate predictions for all pixels in the image. However, using more global context is prone to overfitting. To alleviate this issue, we propose to use data augmentation to generate more data for training. In addition to the data augmentation in 2D image space, we also augment the data in 3D space. We evaluate our approach on the publicly available 7-Scenes dataset, and experiments show that it has better scene coordinate predictions and achieves state-of-the-art results in localization with improved robustness on the hardest frames (e.g., frames with repeated structures).

As road traffic sign recognition is a crucial component for automatic driver assistance systems, it is a key problem in computer vision as well. Therefore, in this paper, we study on the problem of road traffic sign recognition utilising the computer vision technology. The main innovation of this paper is to propose an improved convolutional neural network, and then use it to tackle the road traffic sign recognition problem. Convolutional neural network can learn features from training data set, and a convolutional network contains alternating layers of convolution and pooling. Particularly, RGB traffic images are transformed to grey scale images, and then grey scale images are input to the improved convolutional neural network. Furthermore, the fixed layers are utilised to discover region of interests, and the learnable layers are used to extract features. In general, output information of the proposed two learnable layers are input to the classifier separately, and parameters of learnable layers and the classifier are trained at the same time. Finally, GTSDB data set is chosen to make performance evaluation, among which 600 images and 300 images are regarded as training and testing data set respectively. Experimental results demonstrate that the improved CNN-based traffic sign recognition performs better than the traditional CNN.

One of the classical problems in computer vision is the automatic identification of different gestures or motions from a sequence of frames, captured via cameras or sensors, that usually contain angles or positions of many body joints. A large body of research addressing this problem exists in the literature. However, an interesting variant is not just to identify the gesture, but to decide whether a certain gesture is correctly or incorrectly executed. This can be in the context of physical exercises for rehabilitation in healthcare, robotics, sports, sign language and more. In this work we present our research on the automatic classification of gestures into correct or incorrect categories using the following three different but powerful techniques: convolutional neural networks (CNNs), long short-term memory (LSTM) neural networks and a technique based on rough path theory to extract unique sequences (i.e. path signatures) from gesture data and to use them as inputs to classical classifiers such as RandomForest (RF) and k-Nearest Neighbor (kNN). We collected the data we used as part of a collaborative project from Perkeso Tun Razak Rehabilitation Centre, Malacca, Malaysia. We recorded 17 patients performing nine types of gestures. For controls, we recorded 14 healthy individuals performing the same gestures. Our cross subject evaluation yields high accuracy for several subjects and gestures. CNNs and LSTMs achieve accuracy values up to 100% for several subjects in many gestures with the highest average accuracy for some gestures reaching 92%. The best overall classifier when using the rough paths representation was kNN as its average accuracy can reach 96.74% (100% accuracy for a subset of subjects in some gestures). For the three methods, the average accuracy across all gestures is 85.24%, 85.63% and 94.67% respectively. Overall, our research shows a great potential in identifying the right learning algorithm in motion correctness identification for real data.

Scene text detection is a crucial step in end-to-end scene text recognition, a greatly challenging problem in computer vision. This paper proposes a novel scene text detection method that involves superpixel-based stroke feature transform (SSFT) and deep learning based region classification (DLRC). The SSFT is developed for candidate character region (CCR) extraction, which consists in partitioning an input image into several regions via superpixel-based clustering, removing most regions based on predefined criteria satisfied by the characters, and refining the remaining regions to obtain CCRs by computing a stroke width map. The character regions are identified from the CCRs using DLRC, in which several hand-crafted low-level features, i.e., color, texture, and geometric features, and some deep convolution neural network (CNN) based high-level features are first extracted from the regions, and then these features are fused by using two fully connected networks (FCNs) for region classification. In the DLRC step, the deep feature extraction CNN and the feature fusion FCNs are jointly trained. Next, the extracted character regions are merged to form candidate text regions, from which the final scene texts are detected. The proposed method is evaluated on three publicly available datasets: ICDAR2011, ICDAR2013, and street view text. It achieves F -measures of 0.876, 0.885, and 0.631, respectively, which demonstrate the effectiveness of the proposed scene text detection method.

Age estimation based on the human face remains a significant problem in computer vision and pattern recognition. In order to estimate an accurate age or age group of a facial image, most of the existing algorithms require a huge face data set attached with age labels. This imposes a constraint on the utilization of the immensely unlabeled or weakly labeled training data, e.g., the huge amount of human photos in the social networks. These images may provide no age label, but it is easy to derive the age difference for an image pair of the same person. To improve the age estimation accuracy, we propose a novel learning scheme to take advantage of these weakly labeled data through the deep convolutional neural networks. For each image pair, Kullback-Leibler divergence is employed to embed the age difference information. The entropy loss and the cross entropy loss are adaptively applied on each image to make the distribution exhibit a single peak value. The combination of these losses is designed to drive the neural network to understand the age gradually from only the age difference information. We also contribute a data set, including more than 100 000 face images attached with their taken dates. Each image is both labeled with the timestamp and people identity. Experimental results on two aging face databases show the advantages of the proposed age difference learning system, and the state-of-the-art performance is gained.

Novel view synthesis is an important problem in computer vision and graphics. Over the years a large number of solutions have been put forward to solve the problem. However, the large-baseline novel view synthesis problem is far from being solved. Recent works have attempted to use Convolutional Neural Networks (CNNs) to solve view synthesis tasks. Due to the difficulty of learning scene geometry and interpreting camera motion, CNNs are often unable to generate realistic novel views. In this paper, we present a novel view synthesis approach based on stereo-vision and CNNs that decomposes the problem into two sub-tasks: view dependent geometry estimation and texture inpainting. Both tasks are structured prediction problems that could be effectively learned with CNNs. Experiments on the KITTI Odometry dataset show that our approach is more accurate and significantly faster than the current state-of-the-art. The code and supplementary material will be publicly available. Results could be found here this https URL

The article considers the possibilities of using the deep learning convolutional neural network ResNet in computer vision and image classification problems. The interpretation of the ResNet network and the datasets used for its training are presented, as well as a method for training a deep convolutional neural network with stochastic depth, which allows significantly reducing errors in the test sample.

Early fire detection is an important factor that can reduce economic and environmental damage and reduce the number of victims. Despite the growing popularity of neural networks as a modern method for solving problems in computer vision, methodological problems often arise in works in this subject area, leading to a decrease or complete devaluation of practical results. This study is devoted to finding such problems among existing works on fire detection. The first section contains a contrast analysis of two works, during which 11 meta-criteria were identified to assess the quality of studies. The second section contains an overview of several works devoted to fire detection in various conditions, both by «classical» methods and using convolutional neural networks. The importance of the correct choice of metrics, the need to choose a model as a process, and a full description of the source data are shown.

Co-Detection is an important problem in computer vision, which involves detecting common objects from multiple images. In this paper, we address the co-detection problem and propose an integrated deep learning model involving two networks for co-detection. Our proposed model detects the objects of individual images using a convolutional neural network by generating the saliency maps, which are passed as input in a Siamese neural network to ascertain whether the salient objects in both the images are similar or different. We have tested our model on the iCoseg dataset achieving high-quality results.

Image classification is a fundamental problem in computer vision, which deserves much attention in the past decade. To provide a comprehensive recall for the image classification task based on the deep learning algorithms, this paper first provides a brief history of computer vision and convolutional neural networks. Then, the current state of research and the direction of development of deep learning-based convolutional neural network models for image classification are examined. In addition, the basic model structure, convolution feature extraction, and pooling operations of standard and convolutional neural networks are also introduced. This paper summarizes the development of convolutional neural network models in recent years. In summary, based on the review of the development of image classification algorithms at home and abroad, the current mainstream image classification algorithms and frontier progress are summarized and analyzed, and the existing problems and future development directions of image classification are summarized and prospected. It can be concluded that deep learning-based methods has a great potential in this case.

Detecting emotion from facial expression has become an urgent need because of its immense applications in artificial intelligence such as human-computer collaboration, data-driven animation, human-robot communication etc. Since it is a demanding and interesting problem in computer vision, several works had been conducted regarding this topic. The objective of this research is to develop a facial expression recognition system based on convolutional neural network with data augmentation. This approach enables to classify seven basic emotions consist of angry, disgust, fear, happy, neutral, sad and surprise from image data. Convolutional neural network with data augmentation leads to higher validation accuracy than the other existing models (which is 96.24%) as well as helps to overcome their limitations.

Convolutional Neural Networks (CNNs) have recently been utilized in a wide range of applications, including image and pattern identification, voice recognition, biometric embedded vision, food recognition, and video analysis for surveillance, industrial robots, and autonomous vehicles. Convolutional neural networks (CNNs) are gaining popularity for a variety of reasons. Feature extractors are created by hand in classic image recognition models. The weights of the convolutional layer utilized for feature extraction, as well as the fully connected layer, are used for classification in CNNs, and these weights are set throughout the training phase. The goal of this study is to evaluate a few convolutional neural network (CNN) learning machine approaches for image recognition. Furthermore, machine learning algorithms are used extensively in contemporary approaches to picture recognition. This article focuses on the development trend of convolution neural network (CNNs) model owing to various learning methods in image recognition during the 2000s, which is largely introduced from the angles of capturing, verification, and clustering, based on twenty five journals that have been reviewed. As a result, deep convolutional neural networks (DCNNs) have been very effective in a variety of machine learning and computer vision problems because they provide a large quality gain at a low computational cost. This training approach also enables models with many processing layers to learn different degrees of abstraction for data representation.

\n Hand pose estimation is a challenging problem in computer vision with a wide range of applications, especially in human-computer interface. With the development of inexpensive consumer-level depth cameras and the evolution on deep learning techniques, the current state-of-art in the problem is continuously developing and several new methods have been proposed in recent years. Those methods are mostly data-driven and reach good results in standard datasets such as NYU, ICVL and HANDS17. An application that would benefit from the use of computer vision techniques is hand occupational therapy. In chronic diseases like rheumatoid arthritis (RA), the evaluation of the hand functional state is fundamental for the treatment and prevention of finger deformities. One of the procedures for deformity diagnosis is the measurement of movement angles i.e. flexion/extension and abduction/addution, made using goniometers in a process that can be time-consuming and invasive for the patient. The main proposal of this PhD is to fill a gap in the literature by proposing and evaluating the viability of using a framework composed of a 3D low-cost sensor and a 3D hand pose estimation state-of-art method for automatic assessment of rheumatoid arthritis patients. Given depth maps as input, our framework estimates 3D hand joint positions using a deep convolutional neural network. The proposed pose estimation algorithm can be executed in real-time, allowing users to visualise 3D skeleton tracking results at the same time as the depth images are acquired. Once 3D joint poses are obtained, our framework estimates flexion/extension and abduction/adduction angles by applying computational geometry oper- ations. The absence of public datasets with RA patients in the literature makes the estimation of hand poses of patients a challenge for computer vision data-driven methods. We therefore proposed a protocol to acquire new data from groups of patients and control. We performed experiments of identification of RA patients and control sets and also performed comparison with goniometer data. Results show that a method based on Fourier descriptors is able to perform automatic discrimination of hands with Rheumatoid Arthritis (RA) and healthy pa- tients. The angle between joints can be used as an indicative of current movement capabilities and function. The acquisition is much easier, non-invasive and patient-friendly, significantly reducing the evaluation time and offering real-time data for the dynamic movement.\n

Predicting panoramic indoor lighting from a single perspective image is a fundamental but highly ill-posed problem in computer vision and graphics. To achieve locale-aware and robust prediction, this problem can be decomposed into three sub-tasks: depth-based image warping, panorama inpainting and high-dynamic-range (HDR) reconstruction, among which the success of panorama inpainting plays a key role. Recent methods mostly rely on convolutional neural networks (CNNs) to fill the missing contents in the warped panorama. However, they usually achieve suboptimal performance since the missing contents occupy a very large portion in the panoramic space while CNNs are plagued by limited receptive fields. The spatially-varying distortion in the spherical signals further increases the difficulty for conventional CNNs. To address these issues, we propose a local-to-global strategy for large-scale panorama inpainting. In our method, a depth-guided local inpainting is first applied on the warped panorama to fill small but dense holes. Then, a transformer-based network, dubbed PanoTransformer, is designed to hallucinate reasonable global structures in the large holes. To avoid distortion, we further employ cubemap projection in our design of PanoTransformer. The high-quality panorama recovered at any locale helps us to capture spatially-varying indoor illumination with physically-plausible global structures and fine details.