preview

Block Diagram Of Proposed System

Decent Essays
IV. PROPOSED SYSTEM

A. Block diagram

Fig 3: Block Diagram of Proposed System

B. Proposed system
In mostly emotion recognition system use Principal Component Analysis (PCA) algorithm for detection. However, in that detection of action unit not done properly so it has some limitation. Recognizing emotion from ensemble of features uses patch descriptors like histogram of oriented gradients, local binary patterns and scale invariant feature transform. It has two outcomes one is person specific and another is person independents. However, by comparing both we can say that person dependent emotion recognition system has better performance.
The basic flow of algorithm is as show in Fig 3 As our aim is to do real time state of mind, detection of human so input image directly taken from webcam video. Therefore, we take few second video as input then extracting the frames from that video. After that number of frames, we apply some basic function on that image to improve the image quality. Colour image more complex for processing so that we convert tis colour image to the grey scale image.

Fig 4: Image processing flow for a single image.

Most real-time video processing and computer vision systems require a stream processing architecture, in which video frames from a continuous stream are processed one (or more) at a time. Live video processing is more complex as the input signal data is more due to live video, instead of that if we use offline video to system and generate
Get Access