Efficient Clothing Pattern Recognition for Blind People Using SVM Classifier

Choosing cloths with complex patterns and colors is a challenging task for visually impaired people. For that we aimed at a practical system magic closet, for automatic occasion oriented clothing recommendation. Given a user input occasion, e. g. , wedding, shopping or dating, magic store room brilliantly proposes the most suitable clothing from the users own apparel photograph collection. Automatic clothing pattern recognition is also a challenging exploration issue due to rotation, scaling, illumination, and particularly vast intraclass pattern variations. Here we developed a camera based prototype system that perceives dress patterns in four classifications (plaid, striped, irregular and patternless) and identifies 11 attire colors. The system integrates a camera, a microphone, a computer, and a Bluetooth earpiece for sound depiction of clothing patterns and colors. A cam mounted upon a pair of sunglasses is used to catch dress pictures. The clothing patterns and colors are described to visually impaired people verbally. This system can be controlled by speech input through microphone. To perceive apparel patterns, proposed a novelRadon signature descriptor and a schema to separate measurable properties from wavelet subbands to capture global features of clothing patterns. More specifically the clothing attributes are dealt with as idle in our proposed inert support vector machine (SVM) based recommendation model. The wearing appropriately measure is described in the model through a highlight event potential and a quality event potential, while the wearing aesthetically foundation is communicated by a characteristic attribute potential. The prototype was additionally utilized by ten outwardly impatient members. Most thought such a system would support more autonomy in their day by day life but they likewise made proposals for upgrades.