High-dimensional Indexing Scheme Research Articles

스파크 환경에서 내용 기반 이미지 검색을 위한 효율적인 분산 인-메모리 고차원 색인 기법

영상에서 범죄 행위 모니터링 및 추적을 위해서 이미지 내에 포함된 객체를 검색하는 내용 기반 검색이 활용되고 있다. 본 논문에서는 내용 기반 이미지 검색을 위해 이미지 또는 객체에서 추출한 대용량 특징 벡터를 이용한 유사도 검색을 지원하는 분산 인-메모리 기반 고차원 색인 기법을 제안한다. 대용량 분산 처리를 위해 빅데이터 플랫폼인 스파크를 활용하고 효율적인 분산 질의 처리 할당을 위해 마스터/슬레이브 모델을 활용한다. 마스터에서는 데이터 및 질의 분배를 수행하고 슬레이브에서는 데이터를 색인한다. 더불어 기존 분산 고차원 색인 기법에서 k-최근접 질의 처리의 성능 문제를 해결하기 위해서 밀집도 및 탐색 비용을 고려한 k-최근접 질의 최적화 기법을 제안한다. 제안하는 기법의 우수성 및 타당성을 입증하기 위해 다양한 성능 평가를 수행한다.

Interactive high-dimensional index for large Chinese calligraphic character databases

The large numbers of Chinese calligraphic scripts in existence are valuable part of the Chinese cultural heritage. However, due to the shape complexity of these characters, it is hard to employ existing techniques to effectively retrieve and efficiently index them. In this article, using a novel shape-similarity- based retrieval method in which shapes of calligraphic characters are represented by their contour points extracted from the character images, we propose an interactive partial-distance-map (PDM)- based high-dimensional indexing scheme which is designed specifically to speed up the retrieval performance of the large Chinese calligraphic character databases effectively. Specifically, we use the approximate minimal bounding sphere of a query character and utilize users' relevance feedback to refine the query gradually. Comprehensive experiments are conducted to testify the efficiency and effectiveness of this method. In addition, a new k -NN search called Pseudo k -NN (P k -NN) search is presented to better facilitate the PDM-based character retrieval.

Multidimensional indexing for recognizing visual shapes

This paper introduces an analytical framework for studying some properties of model acquisition and recognition techniques based on indexing. The goal is to demonstrate that several problems previously associated with the approach can be attributed to the low dimensionality of invariants used. These include limited index selectivity. Excessive accumulation of votes in the look-up table buckets, and excessive sensitivity to quantization parameters. Theoretical results demonstrate that using high-dimensional, highly descriptive global invariants produces better results in terms of accuracy, false positive suppression, and computation time. A practical example of high-dimensional global invariants is introduced and used to implement a 2-D shape acquisition/recognition system. The acquisition/recognition system is based on a two-step table look-up mechanism. First, local curve descriptors are obtained by correlating image contour information at short range. Then, seven-dimensional global invariants are computed by correlating triplets of local curve descriptors at longer range. This experimental system is meant to illustrate the behavior of a high-dimensional indexing scheme. Indeed, its performance shows good agreement with the analytical model with respect to database size, fault tolerance, and recognition speed. Model acquisition time is linear to cubic in the number of object features. Object recognition time is constant to linear in the number of models in the database and linear to cubic in the number of features in the image. The system has been tested extensively. With more than 250 arbitrary shapes in the database. Unsupervised shape and subpart acquisition is demonstrated.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>