Обнаружение транспортных средств на изображениях загородных шоссе на основе метода Single shot multibox Detector

Long short-term memory (LSTM) has transformed both machine learning and neurocomputing fields. According to several online sources, this model has improved Google’s speech recognition, greatly improved machine translations on Google Translate, and the answers of Amazon’s Alexa. This neural system is also employed by Facebook, reaching over 4 billion LSTM-based translations per day as of 2017. Interestingly, recurrent neural networks had shown a rather discrete performance until LSTM showed up. One reason for the success of this recurrent network lies in its ability to handle the exploding/vanishing gradient problem, which stands as a difficult issue to be circumvented when training recurrent or very deep neural networks. In this paper, we present a comprehensive review that covers LSTM’s formulation and training, relevant applications reported in the literature and code resources implementing this model for a toy example.

A review on the long short-term memory model

Previous works have shown that the ear is a promising candidate for biometric identification. However, in prior work, the preprocessing of ear images has had manual steps and algorithms have not necessarily handled problems caused by hair and earrings. We present a complete system for ear biometrics, including automated segmentation of the ear in a profile view image and 3D shape matching for recognition. We evaluated this system with the largest experimental study to date in ear biometrics, achieving a rank-one recognition rate of 97.8 percent for an identification scenario and an equal error rate of 1.2 percent for a verification scenario on a database of 415 subjects and 1,386 total probes.

Biometric Recognition Using 3D Ear Shape

We propose a novel geometric framework for analyzing 3D faces, with the specific goals of comparing, matching, and averaging their shapes. Here we represent facial surfaces by radial curves emanating from the nose tips and use elastic shape analysis of these curves to develop a Riemannian framework for analyzing shapes of full facial surfaces. This representation, along with the elastic Riemannian metric, seems natural for measuring facial deformations and is robust to challenges such as large facial expressions (especially those with open mouths), large pose variations, missing parts, and partial occlusions due to glasses, hair, and so on. This framework is shown to be promising from both-empirical and theoretical-perspectives. In terms of the empirical evaluation, our results match or improve upon the state-of-the-art methods on three prominent databases: FRGCv2, GavabDB, and Bosphorus, each posing a different type of challenge. From a theoretical perspective, this framework allows for formal statistical inferences, such as the estimation of missing facial parts using PCA on tangent spaces and computing average shapes.

/pdf/3d-face-recognition-under-expressions-occlusions-and-pose-26qgp6f3vp.pdf

3D Face Recognition under Expressions, Occlusions, and Pose Variations

http://www4.comp.polyu.edu.hk/~csajaykr/myhome/papers/PR2011.pdf

Automated human identification using ear imaging

In this paper we investigate the use of outer ear images for human identification. From the point of view of image processing, ears offer several advantages over complete faces: reduced spatial resolution, a more uniform distribution of colour, and less variability with expressions and orientation of the face. These advantages together with its identification richness, make ear images appropriate to be used as input data for a connectionist system. A new multiple identification method, which combines the results obtained by several neural classifiers using, respectively, features outer ear points, information obtained from ear shape and wrinkles, and macrofeatures extracted by a compression network, is presented. Experimental results yields higher identification rates as well as a more robust framework using this approach as a component of a more general face identification system especially in security applications.

On the use of outer ear images for personal identification in security applications

Offline continuous handwriting recognition using sequence to sequence neural networks

Support vector machines versus multi-layer perceptrons for efficient off-line signature recognition

Thirty local geometrical features extracted from 3D hitman face surfaces have been used to model the face for face recognition. They are the most discriminating ones selected from a set of 86. We have experimented with 420 3D-facial meshes (without texture) of 60 individuals. There are 7 images per subject including views presenting fight rotations and facial expressions. The HK algorithm, based in the signs of the mean and Gaussian curvatures, has been used for region segmentation. Experiments under controlled and non-controlled acquisition conditions, considering pose variations and facial expressions, have been achieved to analyze the robustness of the selected characteristics. Success recognition results of 82.0% and 90.16% were obtained when the images are frontal views with neutral expression using PCA and SVM, respectively. The recognition rates only decrease to 76.2% and 77.9% using PCA and SVM matching schemes respectively, under gesture and light face rotation.

Face recognition using 3D local geometrical features: PCA vs. SVM

The management of solid waste in large urban environments has become a complex problem due to increasing amount of waste generated every day by citizens and companies. Current Computer Vision and Deep Learning techniques can help in the automatic detection and classification of waste types for further recycling tasks. In this work, we use the TrashNet dataset to train and compare different deep learning architectures for automatic classification of garbage types. In particular, several Convolutional Neural Networks (CNN) architectures were compared: VGG, Inception and ResNet. The best classification results were obtained using a combined Inception-ResNet model that achieved 88.6% of accuracy. These are the best results obtained with the considered dataset.

José Francisco Vélez

Papers

On the use of outer ear images for personal identification in security applications

Offline continuous handwriting recognition using sequence to sequence neural networks

Support vector machines versus multi-layer perceptrons for efficient off-line signature recognition

Face recognition using 3D local geometrical features: PCA vs. SVM

Automatic Image-Based Waste Classification