Fpga Based Implementation Of Digit Recognition

The advantages of this method are that it is accurate, specific, and fairly easy to perform (Randolph, 1975). One

The name MATLAB stands for Matrix Laboratory, and the language syntax and commands are based on matrix operations and their extensions. In its simplest form a matrix is a set of numbers or elements arranged in a rectangular grid of horizontal rows and vertical columns. Every row or column in a matrix is also called a vector. One of the strengths of MATLAB is its ability to handle collection of numbers, called array. An array with m rows and n columns is referred as an m times n matrix, denoted by m × n indicating the size or the matrix dimension, consisting of a total number of m * n elements. The elements of a matrix are indexed. The purpose of indexing is to make easier the identification process of each element of a matrix by using one or more subscripts. A constant or scalar can be considered a special matrix consisting of 1 row by 1 column, or a 1 × 1 matrix. Similarly, a vector may be viewed as a one dimensional (1-D) array, where one of the indexes is 1, which is usually omitted. A 2-D array is the typical matrix structure encountered in most applications and requires two indexes. The first identifies the row followed by a comma and the second identifies the column. Matrices and vectors are frequently enclosed in brackets when used in MATLAB. The elements of a matrix or vector can be real or complex numbers, strings, symbolic expressions, or in general any MATLAB function or expression. A vector consisting of only one row

It required a lot of study on previous work and some study of related topics which uses a little bit same technique to process their features for recognizing a person. Most of the literatures were based on palm image processing and some of the books and research papers were based on face recognition. As such, a lot of research work has been done by Chinese researchers so far. A series of researches gave me a set of methods and a set of features to be selected among them.

We have intentionally separated thresholding technique from region based due the usage of histogram and its simplicity. A lot of limitations are faced while applying segmentation namely:

Fig. 7 and Fig. 8 have been obtained with the same ranging algorithm for comparison.

Features are essential for any classification or analysis in image processing. There are many types of features which can be extracted from the images each gives its identical informations about the image. Here MA region supposed with properties such as shape, color and size which appears as a dark red colored circle shape. To identify MA and non- MA region feature vectors are formed for each candidate regions.

It has been watched that regularly Hard Exudates and Optic plate are of same splendor, shading and differentiate.Along these lines, here and there optic circle is misassumed and must be dispensed with from the results of Hard Exudates got after applying a grouping calculation to get exact Hard Exudates.Here, Circular Hough Transform is connected to the outcome acquired by applying a bunching calculation for distinguishing optic circle.when the optic circle in distinguished it is has been existed and finally the results of the hard exudates is obtained.

Abstract— In this paper two set of edge-texture features is proposed such as Discriminative Robust Local Binary Pattern (DRLBP) and Discriminative Robust Local Ternary Pattern (DRLTP) for object recognition. The proposed DLBP and DRLTP are derived from the drawback of the Local Binary Pattern (LBP), Local Ternary Pattern (LTP) and Robust LBP (RLBP).The LBP code and the RLBP code are mapped in the same block .The proposed feature solves the problem of discrimination between a bright object against dark background and vice-versa. The proposed feature retains contrast information for representation of object contours the LBP, LTP and RLBP discards. By this proposed features the objects in the image can be further analyzed for the exact location of the object in the given image.

Various classification methods have been developed to extract information from imageries. The two main types are pixel and object-based methods. Pixel-based methods can be cluster based unsupervised or supervised classification whereas the later uses statistical (e.g., maximum likelihood algorism) and non-statistical algorithms (e.g., support vector machines) (Lu, Li, Kuang, & Moran, 2014). The object-based classification which overcomes some of the particular problems encountered with pixel-based classification (Blaschke, 2010) was used to analyze

Scilab with dynamically typed objects it is a interpreted language . Scilab runs is available in binary format, for the platforms: Unix/Linux workstations MacOSX. MacOSX and Windows, users can also be installed using Scilab. Compilation of source code is also possible in Scilab. Scilab was named Basil, developed at INRIA as part of the Meta2project. It was developed in the name of Scilab by the Scilab group, which comprised of a team of INRIA Metal au and ENPC. Since 2004, Scilab development was been coordinated by a consortium .Scilab is used as a scripting language to test algorithms and to perform computations numerical. Scilab is a programming language, and around 2000 Scilab coded functions are available in library . The Scilab syntax is very simple, and also which are the fundamental object of scientific calculus the uses the matrices, and it is provided with specific functions and operators. Matrices are of different types which includes real, complex, string, polynomial, and rational. Scilab programs are very quiet compact and they are smaller than their counterparts in C, C++, or Java. Scilab is mainly a combination of scientific computing, numerical libraries from such areas as numerical library such as linear algebra, optimization and numerical integration it is a easy access . It is also simple to expand Scilab environment in a computer. Using static or dynamic links, one can easily import new functionalities from external libraries into Scilab . New

Abstract— This paper proposed two set of edge-texture features is such as Discriminative Robust Local Binary Pattern (DRLBP) and Discriminative Robust Local Ternary Pattern (DRLTP) for object recognition. The proposed DLBP and DRLTP are resultant from the disadvantage of the Local Binary Pattern (LBP), Local Ternary Pattern (LTP) and Robust LBP (RLBP).The LBP system and the RLBP system are mapped in the same block .The proposed feature indentifies the problem of discrimination between a bright object against dark background and vice-versa. The proposed feature also retains contrast information for object contours the LBP, LTP and RLBP discards. By the proposed features the objects is further analyzed for the accurate position of the object in the given image.

Feature plays a very important role in the area of image processing. Different feature extraction techniques are applied on different types of images to get features that will be useful in classifying and recognition of images. Features describes the important information of images that helps to classify images correctly and remarkably reduce the dimension of the images.

The simplest way to use image binarization is to choose a threshold value, and classify all pixels with values above this threshold as white, and all other pixels as black. Selecting proper threshold is very important task. In many cases, finding one threshold compatible to the entire image is very difficult, and in many cases even impossible. Therefore, adaptive image binarization is needed where an optimal threshold is chosen for each image area. Binarization is processing of converting color image in to binary image. In binarization, first we are converting color image in to Gray scale image using following formula. [2]There are various Binerization methods and in that various different algorithm used are as follows. Color image is converted into gray image and following algorithms are applied on gray scale image for converting it in to binary image.

The captured input image has number plate covered by vehicle body, so by this step only number plate area is detected and extracted from whole body of vehicle. The number plate extraction phase influence the accuracy of ANPR system because all further step depend on the accurate extraction of number plate area. The input to this stage is vehicle image and output is a portion of image containing the exact number plate. Number plate can be distinguished by its features. Instead of processing every pixel, the system processes only the pixels that have these features. The features are derived from number plate format and the characters constituting the plate. Number plate color, rectangular shape of number plate boundary, the color change between the plate background and characters on it etc. can be used for detection and extraction of number plate area. The extraction of Indian number plate is difficult as compared to the foreign number plate because in India there is no standard followed for the aspect ratio of plate. This factor makes the detection and extraction of number plate very difficult. The various methods used for number plate extraction are as follows:-

Segmenting or dividing a digital image into region of interests or meaningful structures in general plays a momentous role in quite a few image processing tasks. Image analysis, image visualization, object representation are some of them. The prime objective of segmenting a digital image is to change its representation so that it looks more expressive for image analysis. During the course of action in image segmentation, each and every pixel of the image segmentation is assigned a label or value. The pixels that share the same value also share homogeneous traits. The examples can include color, texture, intensity or some other features. Image segmentation can be defined as the technique to divide the an image f (x, y) into a non empty subset f1, f2, ...., fn which is continuous and disconnected. This step contributes in feature extraction. There are quite a few applications where image segmentation plays a pivotal role. These applications vary from image filtering, face recognition, medical imaging