No abstract

-This paper presents a new approach to offline handwritten numeral recognition based on structural and statistical features. Five different types of skeleton features: (horizontal, vertical crossings, end, branch, and cross points), number of contours in the image, Widthto-Height ratio, and distribution features are used for the recognition of numerals. We create two vectors Sample Feature Vector (SFV) is a vector which contains Structural and Statistical features of MNIST sample data base of handwritten numerals and Test Feature Vector (TFV) is a vector which contains Structural and Statistical features of MNIST test database of handwritten numerals. The performance of digit recognition system depends mainly on what kind of features are being used. The objective of this paper is to provide efficient and reliable techniques for recognition of handwritten numerals. A Euclidian minimum distance criterion is used to find minimum distances and knearest neighbor classifier is used to classify the numerals. MNIST database is used for both training and testing the system. A total 5000 numeral images are tested, and the overall accuracy is found to be 98.42%.

Texture refers to the variation of gray level tones in a local neighbourhood. The-local‖ texture information for a given pixel and its neighbourhood is characterized by the corresponding texture unit. Based on the concept of texture unit, this paper describes a new statistical approach to texture analysis, based on average of the both fuzzy left and right texture unit matrix. In this method the-local‖ texture information for a given pixel and its neighbourhood is characterized by the corresponding fuzzy texture unit. The proposed Average Fuzzy Left and Right Texture Unit (AFLRTU) matrices overcome the disadvantage of FTU by reducing the texture unit from 2020 to 79. The proposed scheme also overcomes the disadvantage of the left and right texture unit matrix (LRTM) by considering the texture unit numbers from all the 4 different LRTM's instead of the minimum one as in the case of LRTM. The cooccurrence features extracted from the AFLRTU matrix provide complete texture information about an image, which is useful for texture classification. Classification performance is compared with the various fuzzy based texture classification methods. The results demonstrate that superior performance is achieved by the proposed method.

For a precise texture classification and analysis, a run length matrix is constructed on the Local Binary pattern using fuzzy principles in the present paper. The proposed Run Length Matrix on Fuzzy LBP (RLM-FLBP) overcomes the disadvantages of the previous run length methods of texture classification that exist in the literature. LBP is a widely used tool for texture classification based on local features. The LBP does not provide greater amount of discriminate information of the local structure and it has a various other disadvantages. The main disadvantage of LBP is, that it compares the centre pixel value with its neighbors to derive the one of the three possible values {0, 1, 2}. The basic drawback of this comparison is that it is very sensitive to noise. And a major contrast between the central pixel and its surroundings are easily resulted by the slight fluctuations above or below the value of the Centre Pixel (CP) and its surroundings. To overcome this problem and to represent the missing local information effectively in the LBP, the present study introduced the concept of fuzzy logic on LBP. This overcomes the problem related to noise and contrast. The proposed method initially converts the 3×3 neighborhood in to fuzzy LBP. In the second stage the proposed method constructs the Run Length Matrix on Fuzzy LBP (RLM-FLBP). On these RLM-FLBP texture features are evaluated for a precise texture classification.

'Local Binary Pattern' (LBP)