Deep learning methods have recently achieved impressive performance in the area of visual recognition and speech recognition. In this paper, we propose a hand- writing recognition method based on relaxation convolutional neural network (R-CNN) and alternately trained relaxation convolutional neural network (ATR-CNN). Previous methods regularize CNN at full-connected layer or spatial-pooling layer, however, we focus on convolutional layer. The relaxation convolution layer adopted in our R-CNN, unlike traditional convolutional layer, does not require neurons within a feature map to share the same convolutional kernel, endowing the neural network with more expressive power. As relaxation convolution sharply increase the total number of parameters, we adopt alternate training in ATR-CNN to regularize the neural network during training procedure. Our previous C- NN took the 1st place in ICDAR'13 Chinese Handwriting Character Recognition Competition, while our latest ATR-CNN outperforms our previous one and achieves the state-of-the-art accuracy with an error rate of 3.94%, further narrowing the gap between machine and human observers (3.87%).

Handwritten Character Recognition by Alternately Trained Relaxation Convolutional Neural Network

Recognition of Bangla handwritten characters is a difficult but important task for various emerging applications. For better recognition performance, good feature representation of the character images is a primary requirement. In this study, we investigate a recently proposed machine learning approach called deep learning [1] for Bangla hand written character recognition, with a focus on automatic learning of good representations. This approach differs from the traditional methods of preprocessing the characters for constructing the handcrafted features such as loops and strokes. Among different deep learning structures, we employ the deep belief network (DBN) that takes the raw character images as input and learning proceeds in two steps - an unsupervised feature learning followed by a supervised fine tuning of the network parameters. Unlike traditional neural networks, the DBN is a probabilistic generative model, i.e., we can generate samples from the model and it can fit both the semi-supervised and supervised learning settings. We demonstrate the advantages of unsupervised feature learning through the experimental studies carried on the Bangla basic characters and numerals dataset collected from the Indian Statistical Institute.

Bangla handwritten character recognition using deep belief network

RNN based online handwritten word recognition in Devanagari and Bengali scripts using horizontal zoning

Futures of artificial intelligence through technology readiness levels

Most of the current object detection approaches deliver competitive results with an assumption that a large number of labeled data are generally available and can be fed into a deep network at once. However, due to expensive labeling efforts, it is difficult to deploy the object detection systems into more complex and challenging real-world environments, especially for defect detection in real industries. In order to reduce the labeling efforts, this study proposes an active learning framework for defect detection. First, an Uncertainty Sampling is proposed to produce the candidate list for annotation. Uncertain images can provide more informative knowledge for the learning process. Then, an Average Margin method is designed to set the sampling scale for each defect category. In addition, an iterative pattern of training and selection is adopted to train an effective detection model. Extensive experiments demonstrate that the proposed method can render the required performance with fewer labeled data.

https://www.mdpi.com/1424-8220/20/6/1650/pdf

Deep Active Learning for Surface Defect Detection.

This paper presents a novel segmentation-based and lexicon-driven handwritten English recognition systems. For the segmentation, a modified online segmentation method based on rules are applied. Then, convolutional neural networks are introduced for offline character recognition. Experiments are evaluated on UNIPEN lowercase data sets, with the word recognition rate of 92.20%.

/pdf/handwritten-english-word-recognition-based-on-convolutional-4orao8rw62.pdf

Gang Bai

Papers

Handwritten English Word Recognition Based on Convolutional Neural Networks