Amlan Kundu

Off-line handwritten word recognition using a hidden Markov model type stochastic network

Because of large variations involved in handwritten words, the recognition problem is very difficult. Hidden Markov models (HMM) have been widely and successfully used in speech processing and recognition. Recently HMM has also been used with some success in recognizing handwritten words with presegmented letters. In this paper, a complete scheme for totally unconstrained handwritten word recognition based on a single contextual hidden Markov model type stochastic network is presented. Our scheme includes a morphology and heuristics based segmentation algorithm, a training algorithm that can adapt itself with the changing dictionary, and a modified Viterbi algorithm which searches for the (l+1)th globally best path based on the previous l best paths. Detailed experiments are carried out and successful recognition results are reported. >

Rotation and gray scale transform invariant texture identification using wavelet decomposition and hidden Markov model

In this correspondence, we have presented a rotation and gray scale transform invariant texture recognition scheme using the combination of quadrature mirror filter (QMF) bank and hidden Markov model (HMM). In the first stage, the QMF bank is used as the wavelet transform to decompose the texture image into subbands. The gray scale transform invariant features derived from the statistics based on first-order distribution of gray levels are then extracted from each subband image. In the second stage, the sequence of subbands is modeled as a hidden Markov model (HMM), and one HMM is designed for each class of textures. The HMM is used to exploit the dependence among these subbands, and is able to capture the trend of changes caused by rotation. During recognition, the unknown texture is matched against all the models. The best matched model identifies the texture class. Up to 93.33% classification accuracy is reported. >

Recognition of handwritten script: a hidden Markov model based approach

The handwritten script recognition problem is modeled in the framework of the hidden Markov model. For English text, which is the focus of the present research, the states can be identified with the letters of the alphabet, and the optimum symbols can be generated. In order to do so, a quantitative definition of symbols, in terms of features, is required. Fourteen features (some old, some new) are proposed for this task. Using the existing statistical knowledge about the English language, the calculation of the model parameters is immensely simplified. Once the model is established, the Viterbi algorithm is proposed to recognize the single best optimal state sequence, i.e. sequence of letters comprising the word. The modification of the recognition algorithm to accommodate context information is also discussed. Some experimental results are provided indicating the success of the new scheme.<<ETX>>

Alternatives to variable duration HMM in handwriting recognition

A successful handwritten word recognition (HWR) system using a variable duration hidden Markov model (VDHMM) and the path discriminant-HMM (PD-HMM) strategy is easy to implement. The central theme of the paper is to show that if the duration statistics are computed, it could be utilized to implement a model-discriminant-HMM (MD-HMM) approach for better experimental results. The paper also describes a PD-HMM based HWR system where the duration statistics are not explicitly computed, but results are still comparable to VDHMM based HWR scheme.

A New Algorithm for Image Edge Extraction Using a Statistical Classifier Approach

This correspondence describes a new algorithm for extracting edges from natural images. Starting from a simple image model, the algorithm poses the problem of edge extraction as a statistical classifier problem. The algorithm is capable of extracting and detecting edges from images even in the presence of noise. A step by step mathematical derivation of the algorithm reveals the flexibility of the algorithm with pertinent parameters that can be varied for the specific need of the user. Finally, the proposed edge operator is compared to the well-known Marr-Hildreths edge operator.

Off-line handwritten word recognition (HWR) using a single contextual hidden Markov model

A complete scheme for totally unconstrained handwritten word recognition based on a single contextual hidden Markov model (HMM) is proposed. The scheme includes a morphology- and heuristics-based segmentation algorithm and a modified Viterbi algorithm that searches the (l+1)st globally best path based on the previous l best paths. The results of detailed experiments for which the overall recognition rate is up to 89.4% are reported.<<ETX>>

Local segmentation of biomedical images

In this paper, a new algorithm for local segmentation of biomedical images is presented. First, a relatively small region is selected for segmentation on the basis of dispersion measurement of local gray values. This small region is then segmented using a segmentation algorithm based on quantization approach. While quantizing a signal, the range of input signal is divided into a number of segments. All signal values within a segment are assigned a unique reconstruction value. In segmentation of gray level images, the problem is to classify or code gray values of the pixels into two or more groups. An N-level threshold selection method for segmentation thus becomes the design of an N-level optimal quantizer. This new approach is suitable for a number of biomedical applications where the objects of interest appear as small and localized in the images. Some experimental results are also provided which illustrate the success of the new scheme.

Handwritten word recognition using HMM with adaptive length Viterbi algorithm

The authors have developed a handwritten word recognition scheme based on a single contextual, discrete symbol probability hidden Markov model (HMM) incorporated with an adaptive length Viterbi algorithm. This work attempts to extend the earlier HMM scheme for naturally segmented word recognition to cursive and nonsegmented word recognition. The algorithm presegments the script into characters and/or fractions of characters, dynamically selects the correct segmentation points, determines the word length, and recognizes the word according to the maximum path probability. The HMM is on top of, but independent of, script segmentation and character recognition techniques, and therefore leaves room for further improvement. The experiments have shown promising results and directions for further improvement.<<ETX>>

Recognition of handwritten word: first and second order hidden Markov model based approach

The handwritten word recognition problem is modeled in the framework of the hidden Markov model (HMM). The states of HMM are identified with the letters of the alphabet. The optimum symbols are then generated experimentally using 15 different features. Both the first- and second-order HMMs are proposed for the recognition tasks. Using the existing statistical knowledge of English, the calculation scheme of the model parameters are immensely simplified. Once the model is established, the Viterbi algorithm is used to recognize the sequence of letters consisting the word. Some experimental results are also provided indicating the success of the scheme.<<ETX>>

Double-window Hodges-Lehman (D) filter and hybrid D-median filter for robust image smoothing

The double window Hodges-Lehman filter (DWD-filter) and a hybrid D-median filter (HDM-filter) for robust image smoothing are proposed. An adaptive mixture of the median and the D-filter, the HDM filter first makes decisions about the presence of edges on the basis of a two-way classification of pixels near and around the pixel to be filtered. Subsequently, straightforward D-filtering is used in the absence of edges, and median filtering is used in the presence of edges. The DWD filter uses two windows and D-filtering. The smaller window is used to preserve the details, then the larger window to provide for sufficient smoothing. Detailed simulation results show that the HDM-filter, while retaining all the good properties of the DWD filter, consistently performs better, in terms of signal-to-noise ratio, than the DWD filter and a number of other filters, including the median filter. The DWD filter is shown to have simpler structure, although not necessarily lesser computational complexity. >