Power has become a burning issue in modern VLSI design and integrated circuits; the power consumed by clocking gradually takes a dominant part. The proposed system provided a design to reduce the clock tree power by replacing some flip-flops with fewer multi-bit flip-flops, and also reduces the total power consumption. First, it perform a co-ordinate transformation to identify those flip flops that can be merged and also identify their legal regions in a library. Next step is to build a combination table to enumerate possible combinations of flip-flops provided by the library. The last step is to merge flip-flops in a hierarchical way. Besides power reduction, the objective of minimizing the total wire length is also considered. The time complexity of the proposed algorithm is less than the time complexity of the existing algorithm. According to the experimental results, the proposed algorithm significantly reduces the clock power by 27.9% and area reduced by 18.5%. The running time is very short. By using this method the low power consumed IC’s can be manufactured using CMOS technologies.
The proposed OCR algorithm to retrieve the text in the scanned document images. Here the text detection algorithm based on two machine learning classifiers: one allows generating candidate word regions and the other filters out non-text ones. The extract connected components (CCs) in images by using the maximally stable extremal region algorithm. In CC clustering adaboost classifiers are used to determine whether the region contains text or not. Then using binarization method, the gray image is converted into binary image. The binarization outcomes are subject to OCR and the corresponding result is evaluated with respect to character and word accuracy. As more and more text documents are scanned fast and accurate. Additional performance metrics of the percentage rates of broken and missed text, false alarms, background noise, character enlargement and merging. This effectiveness of the proposed method is also confirmed by tests carried on realistic document images. For proposed algorithm MATLAB version 13 software is used.
The work depends on the development of a wheelchair that can be a fully automatic navigation system. It provides flexible operation to choose different modalities to command the wheel chair, this method is very useful to a people who can affected for charcot-marie-tooth disease. Patients can command the wheelchair based on their eye blinks, eye movement. The wheelchair can operate like an auto-guided vehicle, following IR sensor way. The digital commends from the IR sensor is moved to raspberry pi. It provides commands to be sent to the wheelchair. Several experiments are used in this technique to introduce an effective wheelchair for disabled persons.