08-16-2017, 10:50 PM
In contrast to limitations of classical computing
[attachment=17251]
Problem definition & Requirements
Existing System :-
In contrast to limitations of classical computing, Artificial Neural Networks (ANNs), that were first developed in the mid 1900 s serve for the emulation of human thinking in computation to a meager, yet appreciable extent. Of the several fields wherein they
have been applied, humanoid computing in general and pattern recognition in particular have been of increasing activity. The recognition of visual (optical) characters is a problem of relatively amenable complexity when compared with greater challenges such as recognition of human faces. ANNs have enjoyed considerable
success in this area due to their humanoid qualities such as adapting to changes and learning from prior experience.
Limitation Of Existing System :-
The recognition of characters from scanned images of documents has been a problem that has received much attention in the fields of image processing, pattern recognition and artificial intelligence. Classical methods in pattern recognition do not as such suffice for the recognition of visual characters due to the following reasons:
1. The same characters differ in sizes, shapes and styles from person to
person and even from time to time with the same person.
2. Like any image, visual characters are subject to spoilage due to noise
3. There are no hard-and-fast rules that define the appearance of a visual character. Hence rules need to be heuristically deduced from samples.
4.Need Of New System
Optical Character Recognition
System is developed because the human brain is adaptive to minor changes and errors in visual patterns.
Advantages :-
The neural system has some direct advantages that become apparent at this=>
1. The method is highly adaptive; recognition is tolerant to minor errors and changes in patterns.
2. The knowledge base of the system can be modified by teaching it newer characters or teaching different variants of earlier characters.
3. The system is highly general and is invariant to size and aspect ratio.
4. The system can be made userspecific:
User-profiles of characters can be maintained, and the system can be made to recognize them as per the orientation of the user.
Cost Estimation :-
1. Salaries of system analysis, programmer during the software development stage.
2. Cost of conversion, preparation of data & system manual & other
3. Supportive documents.
4.Cost of new additional hardware.
5.Cost of training employee.
Feasibility Study
Feasibility study is survey of possibility computerization based on the nest management of objectives related to an analysis of the existing facilities within the company.
Feasibility study is done by evaluating the existing system of the area undertakes investigation and generating ideas for new style. The objective of feasibility study is the key factors considered during feasibility are:-
1. Economical feasibility
2. Behavioral feasibility
3. Technical feasibility
4. Operational feasibility
Now, system analyst has to examine whether computerized system is feasible in the point of view off economical, technical and behavioral.