Offline handwritten Arabic words recognition using Zernike moments and Hidden Markov Models

In this work, we investigate the combination of PGM (Propabilistic Graphical Models) classifiers, either independent or coupled, for the recognition of Arabic handwritten words. The independent classifiers are vertical and horizontal HMMs (Hidden Markov Models) whose observable outputs are features extracted from the image columns and the image rows respectively. The coupled classifiers associate the vertical and horizontal observation streams into a single DBN (Dynamic Bayesian Network). A novel method to extract word baseline and a simple and easily extractable features to construct feature vectors for words in the vocabulary are proposed. Some of these features are statistical, based on pixel distributions and local pixel configurations. Others are structural, based on the presence of ascenders, descenders, loops and diacritic points. Experiments on handwritten Arabic words from IFN/ENIT strongly support the feasibility of the proposed approach. The recognition rates achieve 90.42% with vertical and horizontal HMM, 85.03% and 85.21% with respectively a first and a second DBN which outperform results of some works based on PGMs.

A system for writer identification based on Arabic handwritten words was built. First a database of words was gathered and used as a test base. Then, features vectors were extracted from writers' word images. Prior to feature extraction, normalization operations were applied to a word or text line. In this research, we studied the feature extraction and recognition operations on Arabic text, on the identification rate of writers. Since there is no well known database containing Arabic handwritten words for researchers to test, we built a new database of off-line Arabic handwriting text to be used for writer identification research. The proposed database is meant to provide training and testing sets for Arabic writer identification research. Arabic handwritten words were collected from 100 writers. We evaluated the performance of edge-based directional probability distributions as features and other features in Arabic writer identification.

This paper proposes a novel similarity measure between vector sequences. We work in the framework of model-based approaches, where each sequence is first mapped to a Hidden Markov Model (HMM) and then a measure of similarity is computed between the HMMs. We propose to model sequences with semicontinuous HMMs (SC-HMMs). This is a particular type of HMM whose emission probabilities in each state are mixtures of shared Gaussians. This crucial constraint provides two major benefits. First, the a priori information contained in the common set of Gaussians leads to a more accurate estimate of the HMM parameters. Second, the computation of a similarity between two SC-HMMs can be simplified to a Dynamic Time Warping (DTW) between their mixture weight vectors, which significantly reduces the computational cost. Experiments are carried out on a handwritten word retrieval task in three different datasets-an in-house dataset of real handwritten letters, the George Washington dataset, and the IFN/ENIT dataset of Arabic handwritten words. These experiments show that the proposed similarity outperforms the traditional DTW between the original sequences, and the model-based approach which uses ordinary continuous HMMs. We also show that this increase in accuracy can be traded against a significant reduction of the computational cost.

This paper introduces an efficient method for face localization and recognition in color images. The proposed method uses the location of eyes for computation and extraction of a face's bounding ellipse. In this way, parameters of a face's ellipse (center, orientation, major and minor axis), is computed by the location of eyes in a face image. In the next step, we apply Pseudo Zernike Moments (PZM), Zernike Moments (ZM) and Principal Component Analysis (PCA) for feature extraction. For classification of these feature vectors a new structure of RBF neural networks with a novel distance function is introduced and a new method for determination of RBF unit parameters is proposed. Finally, we compare the efficiency of the proposed system for three types of feature vectors (PZM, ZM and PCA). Results emphasize the high accuracy and efficiency of the PZM features proportion to other features (ZM and PCA) for use in the proposed recognition system.

Offline handwritten Arabic cursive text recognition using Hidden Markov Models and re-ranking

This paper proposes an approach combining the set of Krawtchouk moments and HMMs (Hidden Markov Models) for unconstrained offline handwritten Chinese character recognition. The Krawtchouk moments can be effectively used as pattern features in analysis of two-dimensional images. Since the basis set is orthogonal in the discrete domain of the image coordinate space, the implementation of Krawtchouk moments doesn't involve any numerical approximation or coordinate transformation. This property makes Krawtchouk moments superior to conventional, more continuous moments such as Legendre moments and Zernike moments. In the field of character recognition, HMMs architecture has been used widely because of its strong adaptability to written distortion and variability. In this paper, Krawtchouk moments and HMMs are combined to recognize unconstrained offline handwritten Chinese amount in words. Experiments show that the average recognition of Krawtchouk is higher than Zernike and Legendre moments within the HMM framework.

Offline Arabic handwritten word recognition: A transfer learning approach

Hidden Markov models (HMMs) are now widely used for off-line handwriting recognition in many languages and, in particular, in Arabic. As in speech recognition, they are usually built from shared, embedded HMMs at the symbol level, in which state-conditional probability density functions are modeled with Gaussian mixtures. In contrast to speech recognition, however, it is unclear which kinds of features should be used and, indeed, very different feature sets are in use today. Among them, we have recently proposed to simply use columns of raw, binary image pixels, which are directly fed into embedded Bernoulli (mixture) HMMs, that is, embedded HMMs in which the emission probabilities are modeled with Bernoulli mixtures. The idea is to bypass feature extraction and ensure that no discriminative information is filtered out during feature extraction, which in some sense is integrated into the recognition model. In this chapter, we review this idea along with some extensions that are currently providing state-of-the-art results on Arabic handwritten word recognition.

Pseudo-Zernike moments have better feature representation capability, and are more robust to image noise than those of the conventional Zernike moments. However, due to the computation complexity of pseudo-Zernike polynomials, pseudo-Zernike moments are yet to be extensively used as feature descriptors as compared to Zernike moments. In this paper, we propose two new algorithms, namely coefficient method and p-recursive method, to accelerate the computation of pseudo-Zernike moments. Coefficient method calculates polynomial coefficients recursively. It eliminates the need of using factorial functions. Individual order or index of pseudo-Zernike moments can be derived independently, which is useful if selected orders or indices of moments are needed as pattern features. p-recursive method uses a combination of lower order polynomials to derive higher order polynomials with the same index q. Fast computation is achieved because it eliminates the requirements of calculating polynomial coefficients, Bpqk, and power of radius, rk, in each polynomial. The performance of the proposed algorithms on moment computation and image reconstruction, as compared to those of the present methods, are experimentally verified using a set of binary and grayscale images.

This paper proposes a method of facial expression recognition based on Zernike moments and the minimum classification error (MCE) based hidden Markov model (HMM). In the feature extraction of face, the method of Zernike moments feature extraction based on local feature regions is adopted. First, eyes and mouths are segmented from the facial expression image and Zernike moments feature vectors of eyes and mouth are extracted. In the classification of expression, using MCE criteria is adopted to improve the performance of HMM. The results show that the performance of expression recognition system can be improved to some extent by using Zernike moments and MCE criterion.

Two methods, Symbolic Indirect Correlation (SIC) and Style Constrained Classification (SCC), are proposed for recognizing handwritten Arabic and Chinese words and phrases. SIC reassembles variablelength segments of an unknown query that match similar segments of labeled reference words. Recognition is based on the correspondence between the order of the feature vectors and of the lexical transcript in both the query and the references. SIC implicitly incorporates language context in the form of letter n-grams. SCC is based on the notion that the style (distortion or noise) of a character is a good predictor of the distortions arising in other characters, even of a different class, from the same source. It is adaptive in the sense that, with a long-enough field, its accuracy converges to that of a style-specific classifier trained on the writer of the unknown query. Neither SIC nor SCC requires the query words to appear among the references.

Classification of Bisyllabic Lexical Stress Patterns Using Deep Neural Networks

A model-based framework of classification error rate estimation is proposed for speech and speaker recognition. It aims at predicting the run-time performance of a hidden Markov model (HMM) based recognition system for a given task vocabulary and grammar without the need of running recognition experiments using a separate set of testing samples. This is highly desirable both in theory and in practice. However, the error rate expression in HMM-based speech recognition systems has no closed form solution due to the complexity of the multi-class comparison process and the need for dynamic time warping to handle various speech patterns. To alleviate the difficulty, we propose a one-dimensional model-based misclassification measure to evaluate the distance between a particular model of interest and a combination of many of its competing models. The error rate for a class characterized by the HMM is then the value of a smoothed zero-one error function given the misclassification measure. The overall error rate of the task vocabulary could then be computed as a function of all the available class error rates. The key here is to evaluate the misclassification measure in terms of the parameters of environmental-matched models without running recognition experiments, where the models are adapted by very limited data that could be just the testing utterance itself. In this paper, we show how the misclassification measure could be approximated by first computing the distance between two mixture Gaussian densities, then between two HMMs with mixture Gaussian state observation densities and finally between two sequences of HMMs. The misclassification measure is then converted into classification error rate. When comparing the error rate obtained in running actual experiments and that of the new framework, the proposed algorithm accurately estimates the classification error rate for many types of speech and speaker recognition problems. Based on the same framework, it is also demonstrated that the error rate of a recognition system in a noisy environment could also be predicted.

Speech signal analysis aims to identify patterns within data to develop effec tive recognition algorithms. This process primarily utilizes feature extraction techniques such as linear predictive coding (LPC), linear predictive cepstral co efficients (LPCCs), and Mel-frequency cepstral coefficients (MFCCs). These features are crucial for constructing recognition algorithms that leverage both statistical and deep learning methods. While deep learning models require ex tensive datasets, they often prove unsuitable for low-resource languages. The Hidden Markov model (HMM)is the most widely adopted statistical framework in speech processing. However, HMMs are characterized by state-dependent models, where each state interacts only with its neighboring states. This limita tion restricts HMMs from capturing long-term signal properties, highlighting the need for addressing these constraints at the feature extraction stage. Most feature extraction methods rely on short-term signal processing, which further limits the comprehension of speech utterances. To overcome these limitations, alter native methods are necessary to capture more comprehensive patterns. This pa per presents a graph-based approach for analyzing speech trajectories and their temporal properties, which are subsequently validated using HMMs in speech recognition tasks. Graph-based representations on a low-resource Telugu dataset improve recognition accuracy by 13% while reducing processing time compared to traditional LPC.

Assessment of cluster analysis of elastic light scatter profiles for the identification of foodborne Bacteria.