Robust recognition technique for handwritten Kannada character recognition using capsule networks

<p>Automated reading of handwritten Kannada documents is highly challenging due to the presence of vowels, consonants and its modifiers. The variable nature of handwriting styles aggravates the complexity of machine based reading of handwritten vowels and consonants. In this paper, our investigation is inclined towards design of a deep convolution network with capsule and routing layers to efficiently recognize Kannada handwritten characters. Capsule network architecture is built of an input layer, two convolution layers, primary capsule, routing capsule layers followed by tri-level dense convolution layer and an output layer. For experimentation, datasets are collected from more than 100 users for creation of training data samples of about 7769 comprising of 49 classes. Test samples of all the 49 classes are again collected separately from 3 to 5 users creating a total of 245 samples for novel patterns. It is inferred from performance evaluation; a loss of 0.66% is obtained in the classification process and for 43 classes precision of 100% is achieved with an accuracy of 99%. An average accuracy of 95% is achieved for all remaining 6 classes with an average precision of 89%.</p>

Articulated Human Pose Estimation Using Greedy Approach

The goal of this Chapter is to introduce an efficient and standard approach for human pose estimation. This approach is based on a bottom up parsing technique which uses a non-parametric representation known as Greedy Part Association Vector (GPAVs), generates features for localizing anatomical key points for individuals. Taking leaf out of existing state of the art algorithm, this proposed algorithm aims to estimate human pose in real time and optimize its results. This approach simultaneously detects the key points on human body and associates them by learning the global context. However, In order to operate this in real environment where noise is prevalent, systematic sensors error and temporarily crowded public could pose a challenge, an efficient and robust recognition would be crucial. The proposed architecture involves a greedy bottom up parsing that maintains high accuracy while achieving real time performance irrespective of the number of people in the image.

Gravity Control-Based Data Augmentation Technique for Improving VR User Activity Recognition

The neural-network-based human activity recognition (HAR) technique is being increasingly used for activity recognition in virtual reality (VR) users. The major issue of a such technique is the collection large-scale training datasets which are key for deriving a robust recognition model. However, collecting large-scale data is a costly and time-consuming process. Furthermore, increasing the number of activities to be classified will require a much larger number of training datasets. Since training the model with a sparse dataset can only provide limited features to recognition models, it can cause problems such as overfitting and suboptimal results. In this paper, we present a data augmentation technique named gravity control-based augmentation (GCDA) to alleviate the sparse data problem by generating new training data based on the existing data. The benefits of the symmetrical structure of the data are that it increased the number of data while preserving the properties of the data. The core concept of GCDA is two-fold: (1) decomposing the acceleration data obtained from the inertial measurement unit (IMU) into zero-gravity acceleration and gravitational acceleration, and augmenting them separately, and (2) exploiting gravity as a directional feature and controlling it to augment training datasets. Through the comparative evaluations, we validated that the application of GCDA to training datasets showed a larger improvement in classification accuracy (96.39%) compared to the typical data augmentation methods (92.29%) applied and those that did not apply the augmentation method (85.21%).

A Novel Concentric Circular Coded Target, and Its Positioning and Identifying Method for Vision Measurement under Challenging Conditions

Coded targets have been demarcated as control points in various vision measurement tasks such as camera calibration, 3D reconstruction, pose estimation, etc. By employing coded targets, matching corresponding image points in multi images can be automatically realized which greatly improves the efficiency and accuracy of the measurement. Although the coded targets are well applied, particularly in the industrial vision system, the design of coded targets and its detection algorithms have encountered difficulties, especially under the conditions of poor illumination and flat viewing angle. This paper presents a novel concentric circular coded target (CCCT), and its positioning and identifying algorithms. The eccentricity error has been corrected based on a practical error-compensation model. Adaptive brightness adjustment has been employed to address the problems of poor illumination such as overexposure and underexposure. The robust recognition is realized by perspective correction based on four vertices of the background area in the CCCT local image. The simulation results indicate that the eccentricity errors of the larger and smaller circles at a large viewing angle of 70° are reduced by 95% and 77% after correction by the proposed method. The result of the wing deformation experiment demonstrates that the error of the vision method based on the corrected center is reduced by up to 18.54% compared with the vision method based on only the ellipse center when the wing is loaded with a weight of 6 kg. The proposed design is highly applicable, and its detection algorithms can achieve accurate positioning and robust identification even in challenging environments.