Book Cover Recognition
نویسندگان
چکیده
Here we developed a MATLAB based Graphical User Interface for people to check the information of desired books in real-time. The GUI allows user to take photos of the book cover. Then it will automatically detect features of the input image based on MSER algorithm, then it will filter out non-text features based on morphological difference between text and non-text regions. In order to further improve the detection result, we implemented a text character alignment algorithm which significantly improves the accuracy of the original text detection. We also compared the built in MATLAB OCR recognition algorithm and a commonly used open source OCR. To perform better detection results,we implemented post detection algorithm and natural language processing to perform false detection inhibition and word correction. Finally, we linked the detection result to internet to perform online matching. With some tolerance, more than 86% accuracy can be achieved by our algorithm. keywords-Text Recognition, MSER Feature Extraction, Text Box Alignment, Automatic Word Correction.
منابع مشابه
Judging a Book By its Cover
Book covers communicate information to potential readers, but can that same information be learned by computers? We propose using a deep Convolutional Neural Network (CNN) to predict the genre of a book based on the visual clues provided by its cover. The purpose of this research is to investigate whether relationships between books and their covers can be learned. However, determining the genr...
متن کاملReview of five specific books on pattern recognition
$85.50 is the price for the 1,847 pages of reading in pattern recognition contained in the books under re;iew. Except for collections of papers and a book of solicited chapters edited by Mendel and Fu, these are the first texts in statistical and geometric pattein recognition since Nilsson's book Learning Machines, published in 1965. So it is with some ihterest and concern that we examine this ...
متن کاملUrban Vegetation Recognition Based on the Decision Level Fusion of Hyperspectral and Lidar Data
Introduction: Information about vegetation cover and their health has always been interesting to ecologists due to its importance in terms of habitat, energy production and other important characteristics of plants on the earth planet. Nowadays, developments in remote sensing technologies caused more remotely sensed data accessible to researchers. The combination of these data improves the obje...
متن کاملCognitive and environmental predictors of early literacy skills
Not all young children benefit from book exposure in preschool age. It is claimed that the ability to hold information in mind (short-term memory), to ignore distraction (inhibition), and to focus attention and stay focused (sustained attention) may have a moderating effect on children's reactions to the home literacy environment. In a group of 228 junior kindergarten children with a native Dut...
متن کاملAuthenticating ‘Cover to Cover’ Reader Series vis-à-vis Cultural Norms for the Iranian community
This research study was an attempt to explore hidden cultural components in an ELT textbook from Oxford University Press (OUP) titled 'Cover to Cover'. Two research methodologies were relied on to unveil the western ideologies in this series: Firstly, a qualitative review over its reading textbooks was undertaken for authenticating the hidden western values for Iranian contexts. At this stage, ...
متن کامل