Object Recognition from an Image through Features Extracted from Segmented Image

Object recognition is a technological discipline that deals with the process of understanding, design, development and construction of techniques to recognize the objects in the image. The objective of an object recognition system is to make the computer to recognize objects without the assistance of the human. The major problem in designing object recognition is automatic identification of the object with respect to its size, location, orientation and in different illumination conditions. When designing an object recognition system, the following are the two problems to be addressed, the first one is choosing the correct set of features to represent the image and the second one is selecting best classifier for recognition. To solve the first problem, it is important to extract features that should be invariant to the object's transformation like scale, translation and rotation. For the second problem, the classifier should recognize the object with less computation time and should provide high performance. This paper discusses the method of slicing the image into several segments and extracting the features. Keywords— Object Recognition, Feature Extraction, locating object, Classifiers