10-04-2017, 08:11 PM
[attachment=1393]
ABSTRACT
A patent always contains some images along with the text. Many text based systemshave been developed to search the patent database. In this paper, we describe PATSEEKthat is an image based search system for US patent database. The objective is to let theuser check the similarity of his query image with the images that exist in US patents.The user can specify a set of key words that must exist in the text of the patents whoseimages will be searched for similarity. PATSEEK auotamatically grabs images from the USpatent database on the request of the user and represents them through an edge orientationautocorrelogram. L1 and L2 distance measures are used to compute the distance betweentyhe images. A recall rate of 100% for 61% of query images and an average 32% recall ratefor rest of the images. has been observed.