In recent years, the products of voice terminal and image retrieval show the intelligentized trend, but the mature commodities are rare in the market. This paper presents an embedded design method of intelligent voice terminal based on pattern recognition. The design adopts Samsung S3C2410 ARM as target board, Philips Uda1341TS as audio codec, embedded Linux OS as software platform, and speech recognition is implemented through small-vocabulary voice training. To improve the recognized effect, we use the image retrieval technology as an auxiliary tool, which helps speech recognition module create or more accurately find a personal voice-training library. By means of image recognition, the experimental results prove that the effect of speech recognition achieves an average increase of 10 percentages.

No abstract

No abstract

No abstract

Abstract:Image search is becoming an urgent problem of the next generation of search engine. We firstly review the developed situation of image search engine in this paper. Then, the main difficulty and key technologies about this engine are analyzed. Next, the design method is elaborated in detail, which mainly includes image recognition, perceptual hash algorithm, system solution, image retrieval procedure as well as software module, and so on. As a result, we develop an image search engine according to above design methods and implement searching image on the Internet. The testing results finally prove the overall performance of our image search engine is excellent and achieves the desired design requirements. By using data filtering technology and perceptual hash algorithm, the search time-consumed is less than 1 second and is of high search efficiency.