Multimodal biometric systems are preferred as a defense compared to unimodal systems. This study introduces an open access multimodal vein database named FYO with each letter dedicated to each author’s name. The database involves three biometric traits; palm vein, dorsal vein and wrist vein of the same individuals, to explore and enhance research in the area of using these traits to create a spoof-proof multimodal authentication system. The vein images of FYO are acquired using medical vein finder in a controlled environment. Comparisons are performed to show the differences with the existing well known databases and the state-of-the-art recognition algorithms. Hand-crafted feature extractors such as Binarized Statistical Image Features (BSIF), Gabor filter and Histogram of Oriented Gradients (HOG) are applied to show the viability of the vein datasets. Additionally, a deep learning based Convolutional Neural Networks (CNN) architecture is proposed with two models using decision-level fusion of palmar, dorsal and wrist biometric traits on vein images. Unimodal systems, multimodal systems and the proposed architecture are tested on several vein datasets including palmar, dorsal and wrist vein images. Experimental results based on accuracy and computation time on our FYO datasets showed competitive output with that of other databases such as Tongji Contactless Palm Vein database, VERA, PUT, Badawi and Bosphorus hand vein databases. Moreover, the proposed CNN architecture on three vein biometric traits show superior performance compared to hand-crafted methods.
This paper investigates the semantic search performance of search engines. Initially, three keyword-based search engines (Google, Yahoo and Msn) and a semantic search engine (Hakia) were selected. Then, ten queries, from various topics, and four phrases, having different syntax but similar meanings, were determined. After each query was run on each search engine; and each phrase containing a query was run on the semantic search engine, the first twenty documents on each retrieval output was classified as being ldquorelevantrdquo or ldquonon-relevantrdquo. Afterwards, precision and normalized recall ratios were calculated at various cut-off points to evaluate keyword-based search engines and the semantic search engine. Overall, Yahoo showed the best performance in terms of precision ratio, whereas Google turned-out to be the best search engine in terms of normalized recall ratio. However, it was found that semantic search performance of search engines was low for both keyword-based search engines and the semantic search engine.
This study investigates reverse image search performance of Google, in terms of Average Precisions (APs) at various cut-off points, on finding out similar images by using fresh Image Queries (IQs) from the five categories "Fashion", "Computer", "Home", "Sports", and "Toys", in order to have an insight about reverse image search performance of Google and then, motivate the researchers and inform the users. Five fresh IQs with different main concepts were created for each of the five categories. These 25 IQs were run on the search engine and for each, the first 100 images retrieved were evaluated with binary relevance judgment. APs at the cut-off points 20, 40, 60, 80, and 100 were calculated for each category and for all 25 IQs. The performance range is from ~42% for Toys category at the cut-off point 100 to 71% for Home category at the cut-off point 20. When the categories are ignored, Google's performance range is from ~52% at the cut-off point 100 to ~57% at the cut-off point 20. It seems that reverse image search performance of Google needs to be improved.
13 July 2023 in Signal, Image and Video Processing