Indoor Object Recognition System using Combined DCT-DWT under Supervised Classifier
نویسندگان
چکیده
The objective of this proposed work is to recognize the real time small indoor objects from the any scene or image of our working environment for visually impaired. This will be efficiently detect and recognize the indoor objects. The objects are detected and segmented automatically by exploiting the geometrical properties of the image regions. Discrete Wavelet Transform (DWT), Discrete Cosine Transform (DCT) and Combined DCT-DWT are implemented and evaluated for extracting features from the segmented object. In the Training phase, more than hundred objects were used for each category of the objects and dimension reduction of the features has been done for better result. The performance of the object recognition for visually impaired is evaluated along with the corresponding feature selection methods. The performance of the recognition system gives the recognition rate of 94.44% with the usage of Combined DCT
منابع مشابه
Pose Invariant Face Recognition using Hybrid DWT-DCT Frequency Features with Support Vector Machines
Face recognition is a challenging problem and up to date, there is no technique that provides a robust solution to all situations. This paper presents a hybrid approach to pose invariant human face recognition. The proposed scheme is based on a combination of the Discrete Wavelet Transform (DWT) and Discrete Cosine Transform (DCT) analysis on face images. The DWT-DCT domain coefficients are use...
متن کاملFisher Discriminant Analysis (FDA), a supervised feature reduction method in seismic object detection
Automatic processes on seismic data using pattern recognition is one of the interesting fields in geophysical data interpretation. One part is the seismic object detection using different supervised classification methods that finally has an output as a probability cube. Object detection process starts with generating a pickset of two classes labeled as object and non-object and then selecting ...
متن کاملImproved Fuzzy Support Vector Machine for Face Recognition
Abstract: Face recognition is the most emerging research area of the pattern recognition since the early 1990s. This paper presents a new classifier called modified fuzzy support vector machine (MFSVM) by modification in membership function of Fuzzy Support Vector Machine using Combination of Distance Feature, Correlation. We use based on discrete wavelet transform (DWT), discrete Cosine transf...
متن کاملPattern Recognition Based Detection Recognition of Traffic Sign Using SVM
The objective of this work describes a method for Traffic sign detection and recognition from the traffic panel board(signage). It detect the traffic signs especially for Indian conditions. Images are acquired through the camera and it is invariant to size then it is scaled. It consist of the following steps, first, it detect the traffic sign, if it has sufficient contrast from the background t...
متن کاملA Multiple Feature based Novel Approach for Identification of Printed Indian Scripts at Word Level
In a country like India where different scripts are in use, automatic identification of printed script facilitates many important applications such as automatic transcription of multilingual documents and for the selection of script specific OCR in a multilingual environment. In this paper a novel method to identify the script type of the collection of documents printed in seven Indian language...
متن کامل