Syafeeza Ahmad Radzi

Character recognition of license plate number using convolutional neural network

This paper presents machine-printed character recognition acquired from license plate using convolutional neural network (CNN). CNN is a special type of feed-forward multilayer perceptron trained in supervised mode using a gradient descent Backpropagation learning algorithm that enables automated feature extraction. Common methods usually apply a combination of handcrafted feature extractor and trainable classifier. This may result in sub-optimal result and low accuracy. CNN has proved to achieve state-of-the-art results in such tasks such as optical character recognition, generic objects recognition, real-time face detection and pose estimation, speech recognition, license plate recognition etc. CNN combines three architectural concept namely local receptive field, shared weights and subsampling. The combination of these concepts and optimization method resulted in accuracy around 98%. In this paper, the method implemented to increase the performance of character recognition using CNN is proposed and discussed.

Tendency of women in engineering program offerred by UTeM

In past, engineering education is dominated by male society. Furthermore, nature of discipline, perception of society and knowledge of women in engineering is also limited among them. Previously, most women only chose courses that somehow related and perceived by community as suit to them. Nowadays, the history is gradually changed; engineering can also be learned and conquered by women. Women are also accepted and rewarded for their contribution. In Malaysia, this kind of change took place around the end of 1990s when the government announced the Seventh Malaysia Plan (RMK 7); which stresses on the need of additional human power in science and technology. With the urge, women realized that they should rise to the expectation and immersed themselves in this area; which promises more work opportunity in the future. This paper aims to investigate the tendency of women in choosing engineering courses while pursuing their study in Universiti Teknikal Malaysia Melaka (UTeM). The analysis has been done based on the number of female students during enrolment and total of female graduates on the 1st until 4th UTeM convocation (year 2005 until 2008). Women perception and acceptance towards engineering courses can be seen from the result of the analysis. With that, the causes of those changes will be presented and elaborated for further educational purposes improvement.