Papers by mehdi dadashi haji
علوم مراقبتی نظامی, Dec 1, 2021
Proceedings of the 15th International Conference on Image Analysis and Processing, 2009
Document images obtained from scanners or photocopiers usually have a black margin which interfer... more Document images obtained from scanners or photocopiers usually have a black margin which interferes with subsequent stages of page segmentation algorithms. Thus, the margins must be removed at the initial stage of a document processing application. This paper presents an algorithm which we have developed for document margin removal based upon the detection of document corners from projection profiles. The algorithm does not make any restrictive assumptions regarding the input document image to be processed. It neither needs all four margins to be present nor needs the corners to be right angles. In the case of the tilted documents, it is able to detect and correct the skew. In our experiments, the algorithm was successfully applied to all document images in our databases of French and Arabic document images which contain more than two hundred images with different types of layouts, noise, and intensity levels.
Two machine learning approaches a r e introduced for text segmentation. The rst approach is based... more Two machine learning approaches a r e introduced for text segmentation. The rst approach is based on inductive learning in the form of a decision tree and the second uses the Naive Bay e s technique. A set of training data is generated from a wide category of compound text image documents for learning both the decision tree and the Naive Bayes Classiier (NBC). The compound documents used for generating the training data include both machine printed and handwritten texts with diierent fonts and sizes. The 18-Discrete Cosine Transform (DCT) coeecients are used as the main feature to distinguish texts from images. The trained decision tree and the Naive Bayes a r e tested with unseen documents and very promising results a r e obtained, although the later method is more accurate and computationally faster. Finally, the results obtained from the proposed approaches a r e compared and contrasted with one wavelet based approach and it is illustrated that both methods presented in this pape...
The cursive nature of Persian alphabet, and the com-plex and convoluted rules regarding this scri... more The cursive nature of Persian alphabet, and the com-plex and convoluted rules regarding this script cause ma-jor challenges to segmentation as well as recognition of Persian words. We propose a new segmentation algo-rithm for the main stroke of online Persian handwritten words. Using this segmentation, we present a perturba-tion method which is used to generate artificial samples from handwritten words. Our recognition system is com-posed of three modules. The first module deals with the preprocessing of the data. We propose a wavelet-based smoothing technique which enhances the recognition per-formance compared to the conventional widely used tech-nique. The second module is word segmentation into con-vex portions of the global shape which we call Convex Curve Sectors (CCSs). The third module is to analyze those CCSs and use the information for recognition per-formed by Dynamic Time Warping (DTW) technique. Us-ing CCSs provides the DTW-based classifier with a com-pact word represen...
In this paper the Naive Bayes Classifier (NBC) is introduced for text segmentation. A set of trai... more In this paper the Naive Bayes Classifier (NBC) is introduced for text segmentation. A set of training data is generated from a wide category of document images for learning the NBC. The images used for generating the training data include both machine-printed and handwritten text with different fonts, sizes, intensity values and background models. A small subset of the coefficients of a discrete cosine transformed image block is used to classify the block as text or non-text. The NBC decision threshold is optimized on a test set. Experiments carried out on unseen documents show promising results. A comparison with a well-established method for text segmentation indicates advantages of the proposed method.
Assigning proper binary codes to the states of sequential circuits is a long studied problem know... more Assigning proper binary codes to the states of sequential circuits is a long studied problem known as state assignment. The choice of the numbers assigned to the states determines the final hardware structure and implementation requirements of the circuits. Conventional state assignment techniques can not be applied when arbitrary optimality criteria are defined. The problem can actually be seen as a search problem with a huge non-linear space. The nature of the space makes it impossible to find optimal solutions by conducting exhaustive, random or conventional search techniques. In this paper, a CAD tool is introduced which solves the problem for sequential synchronous circuits by means of a Genetic Algorithm (GA). The main advantage of the tool is the ability to cope with large circuits and optimize with respect to different objective functions. Moreover, it is free, easy-to-use and cross-platform.
Document Recognition and Retrieval XXI, 2013
ABSTRACT Separation of keywords from non-keywords is the main problem in keyword spotting systems... more ABSTRACT Separation of keywords from non-keywords is the main problem in keyword spotting systems which has traditionally been approached by simplistic methods, such as thresholding of recognition scores. In this paper, we analyze this problem from a machine learning perspective, and we study several standard machine learning algorithms specifically in the context of non-keyword rejection. We propose a two-stage approach to keyword spotting and provide a theoretical analysis of the performance of the system which gives insights on how to design the classifier in order to maximize the overall performance in terms of F-measure.
2012 International Conference on Frontiers in Handwriting Recognition, 2012
ABSTRACT We present a statistical hypothesis testing method for handwritten word segmentation alg... more ABSTRACT We present a statistical hypothesis testing method for handwritten word segmentation algorithms. Our proposed method can be used along with any word segmentation algorithm in order to detect over-segmented or under-segmented errors or to adapt the word segmentation algorithm to new data in an unsupervised manner. The main idea behind the proposed approach is to learn the geometrical distribution of words within a sentence using a Markov chain or a Hidden Markov Model (HMM). In the former, we assume all the necessary information is observable, where in the latter, we assume the minimum observable variables are the bounding boxes of the words, and the hidden variables are the part of speech information. Our experimental results on a benchmark database show that not only we can achieve a lower over-segmentation and under-segmentation error rate, but also a higher correct segmentation rate as a result of the proposed hypothesis testing.
Pattern Recognition, 2012
The removal of noise patterns in handwritten images requires careful processing. A noise pattern ... more The removal of noise patterns in handwritten images requires careful processing. A noise pattern belongs to a class that we have either seen or not seen before. In the former case, the difficulty lies in the fact that some types of noise patterns look similar to certain characters or parts of characters. In the latter case, we do not know the class of noise in advance which excludes the possibility of using parametric learning methods. In order to address these difficulties, we formulate the noise removal and recognition as a single optimization problem, which can be solved by expectation maximization given that we have a recognition engine that is trained for clean images. We show that the processing time for a noisy input is higher than that of a clean input by a factor of two times the number of connected components of the input image in each iteration of the optimization process. Therefore, in order to speed up the convergence, we propose to use fuzzy inference systems in the initialization step of the optimization process. Fuzzy inference systems are based on linguistic rules that facilitate the definition of some common classes of noise patterns in handwritten images such as impulsive noise and background lines. We analyze the performance of our approach both in terms of recognition rate and speed. Our experimental results on a database of real-world handwritten images corroborate the effectiveness and feasibility of our approach in removing noise patterns and thus improving the recognition performance for noisy images.
The cursive nature of Persian alphabet, and the complex and convoluted rules regarding this scrip... more The cursive nature of Persian alphabet, and the complex and convoluted rules regarding this script cause major challenges to segmentation as well as recognition of Persian words. We propose a new segmentation algorithm for the main stroke of online Persian handwritten words. Using this segmentation, we present a perturbation method which is used to generate artificial samples from handwritten words. Our recognition system is composed of three modules. The first module deals with the preprocessing of the data. We propose a wavelet-based smoothing technique which enhances the recognition performance compared to the conventional widely used technique. The second module is word segmentation into convex portions of the global shape which we call Convex Curve Sectors (CCSs). The third module is to analyze those CCSs and use the information for recognition performed by Dynamic Time Warping (DTW) technique. Using CCSs provides the DTW-based classifier with a compact word representation which makes comparison much faster.
Uploads
Papers by mehdi dadashi haji