ABSTRACT
In this paper the face recognition is done for the visually challenged people. Visually challenged people faces lot of problems in day to day life. Our goal is to make them lead a life which is of security and safety for their own well being. This makes them confident to lead their life normally. The face detection helps them to recognize faces of people known to them within a certain distance.
This paper reduce the difficulty in identifying face of the person used. The face recognition is done using the haar feature base cascade classifiers using Eigen face algorithm. In addition to the face recognition this paper also enhances the process by providing audio output through the e speak software which converts the text to speech. The whole process is designed to run efficiently on a raspberry pi B+ module on opencv platform.
INTRODUCTION
Fig.1.Basic block diagram of face recognition.
Over the years much advancement in technology for the visually impaired people has been developed. The image analysis and detection has been very significant in various applications. The face recognition system has been widely developed in several government sectors across the globe. It can be also used in terrorist screening where the database of the terrorist can be fed to check whether the person which is being screened is the suspect.
This paper provides the real time application of face which will be very useful for the blind people. Several face recognition algorithm and various techniques has been employed in numerous processes. The face recognition is considered to be a very tough process. The existing face recognition system runs on MATlab platform which is not an open source software and is less portable. The PCA technique employed with Eigen face algorithm is widely used. The disadvantages that occur with the usage of PCA technique has been overcome by Haar cascade classifier.
Fig. 3. Principal Component Analysis.
PCA is a method in which is used to simplify the problem of choosing the representation of any eigen values and its corresponding eigen vectors to get a consistent representation. It can be obtained by diminishing the dimensional space of the representation. To obtain fast and robust object recognition, the dimensional space has to be reduced. On the whole, PCA also retains the original information of the data. Eigen face based algorithm applies on the PCA basis.
Fig. 4. Common Haar features.
The core basis for Haar classifier object detection is the Haar-like features. These features, rather than using the intensity values of a pixel, use the change in contrast values between adjacent rectangular groups of pixels. The contrast variances between the areas. Two or three adjacent groups with a relative contrast variance form a Haar-like featureFirst we need to load the required XML classifiers.
RESULTS
Fig. 7. Training Images.
Fig. 8. Face Detection.
Firstly in facial feature detection is detecting the face. This requires analyzing the entire image. The second step is using the isolated face to detect each feature. Since each portion of the image used to detect a feature is much smaller than that of the whole image, detection of all three facial features takes less time on average than detecting the face itself. Using a raspberry pi B+ processor to analyze a 320 by 240 image, a frame rate of 3 frames per second was achieved.
Since a frame rate of 5 frames per second was achieved in facial detection only by using a much faster processor, regionalization provides a tremendous increase in efficiency in facial feature detection. Regionalization also greatly increased the accuracy of the detection. All false positives were eliminated, giving a detection rate of around 95% for the eyes and nose. The mouth detection has a lower rate due to the minimum size required for detection.
FUTURE PLANS
With the detection of facial features, the next goal is to research the ability for more precise details, like some individual points, of the facial features to be gathered. Those will be use to differentiate general human emotions, like happiness and sadness and other emotions. Recognition of human emotions would require accurate detection and analysis of the various elements of a human face, like the brow and the mouth, to determine an individual’s current expression.
The expression can then be compared to what is considered to be the basic signs of an emotion in all human beings. This research will be used in the field human-computer interaction to analyze the emotions one exhibits while interacting with a user interface which was not yet experimented before in the world of science and advancement.
CONCLUSION
This paper gives a contribution for the development of new human-machine interfaces for mobile robots and autonomous systems, based on computer vision techniques. The article presented an approach for real-time face recognition and tracking which can be very useful in human robot interaction environment this system starts with a very fast real-time learning process and then allows the robot to follow the person and to be sure it is always interacting with the right one under a wide range of conditions including: illumination, scale, pose, and camera variation.
The face tracking system works as a preprocessing stage to the face recognition system, which allows it to concentrate the face recognition task in a sub-window previously classified as face. This abruptly reduces the computation time. The introduction of a position predictive stage would also reduce the face search area driving to the creation of a robust automatic tracking and real-time recognition system. This paper also presents a Pre-Learnt User Recognition System which works in almost real-time and that can be used by the human to create a set of known people that can be recognized anytime. The processor has a certain number of people in the database and once a known face is found it can start following and interacting with it. Of course this system can also be used in security applications since it has the ability of tracking a set of known people.
Source: Journal of Chemical and Pharmaceutical Sciences
Authors: K. Revathi | Jaya Bharathi.M | Saranya.U
>> Matlab Projects Fingerprint Recognition and Face detection for Final Year Students
>> More Matlab Projects on Audio Processing for Final Year Students