<title>Shape recognition of irregular objects</title>

The direction chain code has been widely used in image coding and recognition for its simplicity and low storage requirement. However, the researches on how to use chain code for shape retrieval are few. The traditional retrieval methods, chain code histogram (CCH) and Minimize Sum Statistical Direction Code (MSSDC) did not take the distribution feature into consideration. In our previous work, three novel descriptors, chain code distribution vector (CCDV), chain code relativity entropy (CCRE), chain code spatial distribution entropy (CCSDE) are discussed which take full advantage of the statistical feature and the distribution, spatial and relativity feature. In this paper, we compared the five algorithms on a large set of shape database. The experimental results denote the efficiency of each method.

Recognition of handwritten characters is a challenging task because of the variability involved in the writing styles of different individuals. In this paper we propose a quadratic classifier based scheme for the recognition of off-line Devnagari handwritten characters. The features used in the classifier are obtained from the directional chain code information of the contour points of the characters. The bounding box of a character is segmented into blocks and the chain code histogram is computed in each of the blocks. Based on the chain code histogram, here we have used 64 dimensional features for recognition. These chain code features are fed to the quadratic classifier for recognition. From the proposed scheme we obtained 98.86% and 80.36% recognition accuracy on Devnagari numerals and characters, respectively. We used five-fold cross-validation technique for result computation.

Background/Objectives: Shape recognition is the most important issue in image understanding and computer vision. Shape representation is a primary issue in shape recognition. This work aims to image retrieval from image databases based on shape recognition. Methods: The Chain Code Histogram is used to generate a numerical feature vector which is used to describe a given shape; the problems of chain code consist of its sensitivity to rotation, scaling and flipping changes. In this paper, new methods are proposed to solve the problems of image rotation and flipping, by applying the second-moments method to calculating the rotation angle, and analyzing the data of the histogram directions. Findings: The rotation angle of the object and the similarity between the horizontally/ vertically flipping shapes and the original shape. Application: The proposed system works efficiently in recognize both regular and irregular objects for the different categories of the MRI images and results of this research will be useful for the calculate the brain object tilted; research will be extended in near future when we combining this method with color and texture features. Keywords: Chain Code Histogram, Flipping, Image Retrieval, Image Segmentation, Rotation

A study of compression efficiency of 3-D chain codes to represent discrete curves is described. The 3-D Freeman chain code and the five orthogonal change chain directions (5OT) chain code are compared. The 3-D Freeman chain code consists of 26 directions, in 3-D Euclidean space, with no invariance under rotation. The 5OT chain elements represent the orthogonal direction changes of the contiguous straight-line segments of the discrete curve. This chain code only considers relative direction changes, which allows us to have a curve descriptor invariant under rotation, and mirroring curves may be obtained with ease. In the 2-D domain, Freeman chain codes are widely used to represent contour curves. Until now, the authors have had no information of implementing Freeman chain codes to compress 3-D curves. Our contribution is how to implement the Freeeman chain code in 3-D and how to compare it with the recently proposed 5OT code. Finally, to probe our results, we apply the proposed method to three different cases: arbitrary curves, cube-filling Hilbert curves, and lattice knots.

The chain code histogram feature is a simple and effective feature ex- traction technology. This paper proposes improvements based on Chain Code His- togram (CCH) and its first differential characteristics. According to the first Diffe- rential Chain Code Histogram (DCCH), the turning points in the direction are extracted,and the judging method of Direction Turning Point (DTP) is given. We combine CCH and DTP into a new feature, then handwritten digits of MNIST da- tabase are recognized and classified by Support Vector Machine (SVM) classifier. The experimental results proved that the recognition rate of the improved method is not only higher than CCH and first differential CCH, but also closely to the rec- ognition rate of their combination. Obviously, the new combination reduces the feature dimension, improves the speed of training and recognition.

This paper presents a novel pupil center detection method, which is robust to the presence of eyelashes and eyelids. First, a low-intensity region is extracted, and its contour is expressed using Freeman's chain code. The five successive elements of Freeman's chain code are then replaced by their mode value. Subsequently, using the filtered Freeman's chain code, the contour graph is generated as a graph in which a vertex is an element, a directed edge is an adjacent relationship, and an edge weight is a quantization direction. An abstracted contour graph is generated from the contour graph, and the pupil center is detected based on an analysis of the abstracted contour subgraph. An evaluation experiment is conducted to evaluate the performance of the proposed approach. It is thus confirmed that the iris detection rate improved although the processing time increased as compared with those in previous studies. This means that the proposed approach can improve the convenience of iris authentication.

Chain codes are the most size-efficient lossless compression methods for representing rasterised binary objects and contours. Satisfactory compression ratio, low processing cost and low storage requirements of the decoder make chain code technique interesting for storage and transmission of predefined graphical objects in embedded environments. Each element in the chain is encoded to show the relative angle difference between two adjacent pixels along the boundary of an object. The cost of binary bits representing the codes are considered to be equal. Yet, more efficient encoding is possible by considering and applying technique that treats the binary bits differently considering its requirement of storage space, energy consumption, speed of execution and etc. This paper considers cost of binary digits as unequal and proposes a new representation of the eight-direction Freeman chain code based on a variation of Huffman coding technique, which considers cost of bits as unequal. The evaluation and comparison of the cost efficiency between classical Freeman chain code and the new representation of the chain code is provided. Our experiments yield that the proposed representation of Freeman Chain code reduces overall storage/transmission cost of encoded objects considerably with compared to classical Freeman chain code.

In this paper, a new method of the group direction difference chain code representation is presented which can be used to represent the curves or shape borders, and also can be used for the features extraction of shape borders. The idea of this method is to construct a chain codes based on the Freeman chain codes whose values represent the average changes in direction along the boundary of an any shape. For the sake of overcoming the noise in Freeman chain codes, in this paper the concept of direction smoothing is proposed, and a transform from Freeman chain codes to the direction smoothing chain codes is developed. Finally, the method and algorithm for obtaining the group direction difference chain codes are presented.

Optical Character Recognition plays an important role in Digital Image Processing and Pattern Recognition. Even though ambient study had been performed on foreign languages like Chinese and Japanese, effort on Indian script is still immature. OCR in Malayalam language is more complex as it is enriched with largest number of characters among all Indian languages. The challenge of recognition of characters is even high in handwritten domain, due to the varying writing style of each individual. In this paper we propose a system for recognition of offline handwritten Malayalam vowels. The proposed method uses Chain code and Image Centroid for the purpose of extracting features and a two layer feed forward network with scaled conjugate gradient for classification.

This paper deals with a quadratic classifier based scheme for the recognition of off-line handwritten numerals of Kannada, an important Indian script. The features used in the classifier are obtained from the directional chain code information of the contour points of the characters. The bounding box of a character is segmented into blocks and the chain code histogram is computed in each of the blocks. Here we have used 64 dimensional and 100 dimensional features for a comparative study on the recognition accuracy of our proposed system. This chain code features are fed to the quadratic classifier for recognition. We tested our scheme on 2300 data samples and obtained 97.87% and 98.45% recognition accuracy using 64 dimensional and 100 dimensional features respectively, from the proposed scheme using five-fold cross-validation technique.

A challenge for retrieval, recognition and representation of binary objects is to find invariants under different transformations. Rotation invariance allows for example to recognize a shape even if it is rotated. We proposed a method to obtain chain code histograms of skeleton and contour shape of objects. We used two representations: the Freeman chain code (F8) and directional Freeman chain code (AF8) to encode regular and irregular shapes. We compared these techniques and we obtained a sounds method to consider chain code as invariant under intermediate rotations.

In this work, we have proposed modified chain code histogram (CCH) based feature extraction method for handwritten character recognition (HCR) applications. This modified approach explores the dynamic nature of directional information, available in character patterns, by introducing the Differential CCH which is termed as Delta (Δ) CCH. A comparable and higher recognition rate is reported which emphasizes that the dynamic nature of directional information captured by the ΔCCH is as important as that of CCH. All the experiments are conducted on MNIST handwritten numeral database. Finally, an improved recognition rate is observed at higher end by using combination of both the features which shows the effectiveness of dynamic directional feature in the classification of handwritten character patterns.

The success of any character recognition system largely depends on how well the distinguishing features of different characters describe the classes of characters. This paper studies the effect of the combinations of three different feature sets (i.e. chain code histogram (CH), longest run (LR) and Gabor wavelet based (GW) feature) on Bangla handwritten character recognition in order to maximize the number of discriminative features among different character classes. Different combinations of the three feature sets, namely LR & GW, CH & GW, LR & CH, and LR, CH & GW tested on a standard database of Bangla characters revealed that the combination of LR and CH features yielded better recognition accuracy compared to the other cases. It was also observed that size of the feature vectors in the combination played a key role in the recognition process.

A universal chain code compression method

Can burrows-Wheeler transform be replaced in chain code compression?