Facial Age Estimation With Age Difference.

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> .

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.

Robust subspace clustering via penalized mixture of Gaussians

In order to determine the similarity between two planar shapes, which is an important problem in computer vision and pattern recognition, it is necessary to first match the two shapes as good as possible. As sets of allowed transformation to match shapes we consider translations, rigid motions, and similarities. We present a generic probabilistic algorithm based on random sampling for matching shapes which are modelled by sets of curves. The algorithm is applicable to the three considered classes of transformations. We analyze which similarity measure is optimized by the algorithm and give rigorous bounds on the number of samples necessary to get a prespecified approximation to the optimal match within a prespecified probability.

We propose a novel computationally efficient correspondence algorithm to identify the correspondence of similar features of the Reference frame to Search frame in the dynamic image sequence analysis for face tracking. The correspondence of the features between the set of images is the central problem in Computer Vision(CV), Image Analysis(IA) and Pattern Recognition(PR). In these areas Correspondence of features is the combinatorial explosion problem or NP-hard, because of their exhaustive searching for features in the sequence of image frames. This correspondence has three major steps such as segmentation, feature extraction and matching. In this paper we propose block-based segmentation in which the frame which contains the face to be track can be segmented as window of size 20*20 which covers the face. Here we consider the window trace mean is the feature since this is rotation invariant and it covers all the rows and columns of the window and it reduces the dimensionality and finally for matching we used the minimum absolute difference method which does not involves more computations since no multiplication operation is involved. We restrict the searching space to [-3,+3] pixels horizontally and vertically in the search image. Experimental results show that this novel algorithm could achieve much higher computational reduction as compared with full search (FS), Diamond search (DS)[6], Cross Diamond Search (CDS)[7,8] and Area Based Correspondence[14] algorithm for face tracking image sequence while similar prediction accuracy is maintained and it is especially suitable for video conferencing and slow moving dynamic image sequence.

Matching two geometric objects in two-dimensional (2D) and three-dimensional (3D) spaces is a central problem in computer vision, pattern recognition, and protein structure prediction. In particular, the problem of aligning two polygonal chains under translation and rotation to minimize their distance has been studied using various distance measures. It is well known that the Hausdorff distance is useful for matching two point sets, and that the Fréchet distance is a superior measure for matching two polygonal chains. The discrete Fréchet distance closely approximates the (continuous) Fréchet distance, and is a natural measure for the geometric similarity of the folded 3D structures of biomolecules such as proteins. In this paper, we present new algorithms for matching two polygonal chains in two dimensions to minimize their discrete Fréchet distance under translation and rotation, and an effective heuristic for matching two polygonal chains in three dimensions. We also describe our empirical results on the application of the discrete Fréchet distance to protein structure-structure alignment.

Convolutional Neural Networks became a state-of-the-art approach for many different problems of computer vision, pattern recognition, and image processing. However, due to the large number of parameters of these architectures, researchers may find difficult to explain what the networks are using as discriminative patterns. An alternative to better understand the behavior of the learned convolutional kernels is the use of visualization techniques. Currently, visualization techniques are more frequently applied to classification tasks. In this paper, we address the visualization of image-to-image translation. One of the contributions of our work is the possibility to modify a network based on the kernel visualization and achieve superior results.

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).

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.

The transportation system has become a fascinating and active research topic due to its multiple problems; most prior research has focused on traffic forecasting, the advanced driver assistant system (ADAS), and self-driving vehicles. Traffic sign recognition (TSR) is an essential sub-system in ADAS that helps a driver better understand the surrounding environment (obstacles, frost, pedestrians). Automatic recognition of traffic signs is a real-world computer vision challenge and pattern recognition problem. Recently, deep architecture neural networks have shown robust solutions in many areas (health care, agriculture, transportation) due to their ability to handle large amounts of data and excel in complex systems. Therefore, a convolutional neural network (CNN) has been adopted, one of the best deep learning approaches in pattern recognition and image classification for TSR. The proposed architecture has been trained and tested on the German traffic sign recognition benchmark dataset (GTSRB). The results reported accuracy of 99.43% that outperformed human accuracy.KeywordsTraffic sign recognition (TSR)Advanced driver assistant system (ADAS)Deep learningConvolutional neural network (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.

Graph matching is an important and persistent problem in computer vision and pattern recognition for finding node-to-node correspondence between graphs. However, graph matching that incorporates pairwise constraints can be formulated as a quadratic assignment problem (QAP), which is NP-complete and results in intrinsic computational difficulties. This paper presents a functional representation for graph matching (FRGM) that aims to provide more geometric insights on the problem and reduce the space and time complexities. To achieve these goals, we represent each graph by a linear function space equipped with a functional such as inner product or metric, that has an explicit geometric meaning. Consequently, the correspondence matrix between graphs can be represented as a linear representation map. Furthermore, this map can be reformulated as a new parameterization for matching graphs in Euclidean space such that it is consistent with graphs under rigid or nonrigid deformations. This allows us to estimate the correspondence matrix and geometric deformations simultaneously. We use the representation of edge-attributes rather than the affinity matrix to reduce the space complexity and propose an efficient optimization strategy to reduce the time complexity. The experimental results on both synthetic and real-world datasets show that the FRGM can achieve state-of-the-art performance.

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.

One of the fundamental problems of computer vision is to extract 3D shape and motion from images. This can be achieved when a scene or object is observed from different viewpoints or over a period of time. There is a wide range of applications, ranging from digitizing cultural heritage to vision-based autonomous robot navigation. This talk will present several approaches to solve this problem. First, we’ll discuss techniques for 3D shape recovery for static objects and scenes. One particular case is the 3D mapping and localization in large environments from images, e.g. urban 3D reconstruction from vehicleborne cameras or localization from cell-phone images. Next, we’ll shift our focus to modeling dynamic scenes, e.g. people who are moving around. In addition to explicitly 3D modeling an event, we'll consider the possibility to perform video-based rendering from casually captured videos. Speaker Bio-Sketch: Marc Pollefeys is a full professor in the Dept. of Computer Science of ETH Zurich since 2007 where he is the head of the Institute for Visual Computing and leads the Computer Vision and Geometry lab. He currently also remains associated with the Dept. of Computer Science of the University of North Carolina at Chapel Hill where he started as an assistant professor in 2002 and became an associate professor in 2005. Before this he was a postdoctoral researcher at the Katholieke Universiteit Leuven in Belgium, where he also received his M.S. and Ph.D. degrees in 1994 and 1999, respectively. His main area of research is computer vision. One of his main research goals is to develop flexible approaches to capture visual representations of real world objects, scenes and events. Dr. Pollefeys has received several prizes for his research, including a Marr prize, an NSF CAREER award, a Packard Fellowship and a European Research Council Starting Grant. He is the author or co-author of more than 130 peer-reviewed publications. He is the General Chair for the European Conference on Computer Vision 2014 (ECCV), was a Program Co-Chair for the IEEE Conference on Computer Vision and Pattern Recognition 2009 (CVPR), was general/program co-chair of the Third Symposium on 3D Data Processing, Visualization and Transmission and has organized workshops and courses at major vision and graphics conferences and has served on the program committees of many conferences. Prof. Pollefeys is/was on the Editorial Board of the IEEE Transactions on Pattern Analysis and Machine Intelligence and the International Journal of Computer Vision as well as several other journals in computer vision, graphics and robotics.