Abstract
This paper is about a selected few image processing applications. Optical Character Recognition is the translation of images of handwritten, typewritten or printed text into machine-editable text. Then I have introduced the captcha that we so frequently encounter in common websites. An algorithm trying to solve or break a captcha has been explained.
Face detection is a growing and an important tool in security these days. It must be applied before face recognition. There are many methods for recognizing faces and a few of them are discussed in the paper.
Contents
Topic Pg No
Image Processing
Optical character recognition
Captcha
Braking Captcha
Face Detection
Algorithm for Face Detection
References
Image processing
Image processing is any form of signal processing for which the input is an image, such as photographs or frames of video; the output of image processing can be either an image or a set of characteristics or parameters related to the image. Most image-processing techniques involve treating the image as a two-dimensional signal and applying standard signal-processing techniques to it.
Typical Operations
Among many other image processing operations are:
Geometric transformation such as enlargement, reduction, and rotation
Color corrections such as brightness and contrast adjustments, quantization, or conversion to a different color space
Digital compositing or optical compositing (combination of two or more images).
Interpolation, demosaicing, and recovery of a full image from a raw image format.
Image editing (e.g., to increase the quality of a digital image)
Image differencing (to determine changes between images)
Image registration (alignment of two or more images)
Image stabilization
Image segmentation(partitioning a digital image into multiple regions)
Extending dynamic range by combining differently exposed images
2-D object recognition with affine invariance
Optical character recognition
Optical character recognition, usually abbreviated to OCR, is the mechanical or electronic translation of images of handwritten, typewritten or printed text (usually captured by a scanner) into machine-editable text.
OCR is a field of research in pattern recognition, artificial intelligence and machine vision. Though academic research in the field continues, the focus on OCR has shifted to implementation of proven techniques. Optical character recognition (using optical techniques such as mirrors and lenses) and digital character recognition (using scanners and computer algorithms) were originally considered separate fields. Because very few applications survive that use true optical techniques, the OCR term has now been broadened to include digital image processing as well.
Early systems required training (the provision of known samples of each character) to read a specific font. "Intelligent" systems with a high degree of recognition accuracy for most fonts are now common.
4.5 Appling Optical Character Recognition (OCR) to a scanned PDF document to make it text searchable (optional)
In this project, issues regarding the Hough Transform for line detection are considered. The first several sections deal with theory regarding the Hough transform, then the final section discusses an implementation of the Hough transform for line detection and gives resulted images. The program, images, and figures for this project are implemented using the Matlab.
The process of verifying a person’s identity, also called authentication, plays an important role in various areas of everyday life. Any situation with user interaction where the identity is required needs a means to verify the claimed identity. One of the more obvious and commonly known application areas for identity verifying technologies, i.e. authentication, is the Logical Access Control to computer systems, where authenticity is normally established by confirming aclaimed identity with a secret password or PIN code.Traditional methods of confirming the identity of an unknown person rely either upon some secret knowledge (such as a PIN or password) or upon an object the person possesses (such as a key or card). But testing for secret knowledge or the possession of special objects can only confirm the knowledge or presence, and not, that the rightful owner is present. In fact, both could be stolen. Conversely, biometric technology is capable of establishing a much closer relationship between the user’s identity and a particular body, through its unique features or behavior.
A biometric recognition system can be used with a number of physiological characteristics (e.g. fingerprint, palmprint, hand geometry, face, iris, ear shape, and retina vein) and behavioral characteristics (e.g. gait, voice, signature and keystroke dynamics) to provide automatic identification of individuals based on their inherent physical and /or behavioral characteristics. Among these biometrics, iris recognition is one of the most accurate and reliable biometric for identification because of following characteristics (i) Iris pattern has complex and distinctive pattern such as arching ligaments, crypts, corona, freckles, furrows, ridges, rings and a zigzag collarette [1]. (ii) possess 266 degrees-of-freedom in variability and uniqueness in the order of one in 1072 [2].
Biometrics is described as the use of human physical features to verify identity and has been in use since the beginning of recorded history. Only recently, biometrics has been used in today’s high-tech society for the prevention of identity theft. In this paper, we will be understanding biometrics, exploring the history of biometrics, examples of today’s current technology and where biometrics are expected to go in the future.
Feature extraction on the basis of principle lines: Any palm print have several principal lines in it, on the basis of these feature extraction is quiet useful for recognition and extraction of palm print recognition system.
The frequency enhancement routines are: low-pass filter, high pass filter, band pass and band stop filtering and homomorphic filtering etc. Homomorphic filtering result is non-uniform light. The picture in the dynamic range is not clear pictures. The high-pass filter system dependably overlooks picture part and highlighting points of interest. That can speak to high frequency components, enhancing the piece of the edge subtle element. This technique is suitable for edge detection of objects in the image. Because of the low frequency method, the visual effect of the prepared picture is not very good.
Teow, L.N. & Loe, K.F. 2002, 'Robust Vision-Based Feature and Classification Schemes for Off-Line Handwritten Digit Recognition', Pattern Recognition vol. 35, no. 1, pp. 2355-64.
Biometrics is a preset method to recognize a person based on a physiological or behavioral attribute. The present features are face recognition, fingerprints, handwriting, hand geometry, iris, vein, voice and retinal scan. In the early years of the 21st century, we find ourselves persistently moving further away from the stipulation of physical human interface playing a major part of basic everyday tasks. Striding ever closer to an programmed society, we interact more habitually with mechanical agents, unsigned users and the electronic information sources of the World Wide Web, than with our human counterpart. It is therefore possibly sardonic that identity has become such an important issue in the 21st century. Face recognition has been related as the divine Grail of biometric recognition systems, due to a number of noteworthy advantages over other methods of identification.
Image segmentation divides a digital image into multiple regions in order to analyze them. It is also used to distinguish different objects in the image. Several image segmentation techniques have been developed by the researchers in order to make images smooth and easy to evaluate. Famous techniques of image segmentation which are still being used by the researchers are Edge Detection, Threshold, Histogram, Region based methods, and Watershed Transformation.
The FAR achieved is 5.3% and FRR is 4.0. Ali Karouni, Bassam Daya, samia Bahlak [3] introduces the offline signature recognition using neural network approach. The geometrical features extracted and classification using ANN. Obtain the threshold 90%, FAR of 1.6% and FRR of 3% and classification ratio is 93%. Vu Nguyen, Midheal Blumenstein graham Leedham [4] proposed a global feature for offline signature verification problem. The global features based on the boundary of a signature and its projections. The SVM is classifier is used for better accuracy and classification. The first global feature is derived from the total ‘energy’ a writer that uses to create the signature. The second features hire information from the horizontal and vertical projections of signature. FRR is 17.25% and FAR for random and targeted forgeries are 0.08 and
Digital image processing is improving or editing digital images using a personal device or computer. Digital image technique and applications usually take an image as input and produced output. These outputs are a modified image and encoded image etc [3]. Image processing refers to a set of procedures which aims at modifying the appearance and nature of an image is either enhance its pictorial information content for user interpretation or make it suitable enough for developing applications and autonomous machine
Image Enhancement: Image enhancement is among the simplest and most appealing areas of the digital image processing. Basically, the idea behind enhancement techniques is to bring out detail that is esoteric, or simply to highlight certain features of interest in an image. Such as, changing brightness, lightness and contrast etc.
Image shape matching is prime concern in object recognition and identification methods. An image matching is a means of determining the resemblance of one image with the other image. Images are matched based on their shape and texture and it finds variety of applications ranging from image retrieval, object recognition, remote sensing, image classification, image analysis and so on. In general, image matching techniques are classified into structure- based [1] [2] and feature-based [3][4] methods. Structure-based methods compare the shape/ structure and the size of the images, whereas the feature- based methods examine the image features like color and texture in addition to size and shape. Therefore, the image shape and size are the most
Iris recognition is very accurate and distinctive because iris has a complex texture that can produce a substantial amount of information to identify a person. Furthermore, the iris remains almost unchanged from childhood, only minuscule variations are presented. The biometric data is captured using a small and high definition camera that is able to recognize different characteristics of the iris. Moreover, the system can detect the use of contact lens with a fake iris and can realize with the natural movement of the eye if the sample object is a living being. Although initially iris recognition systems were expensive and complex to use, new technology developments have improved these weaknesses.