High Speed and Small Memory Object Recognition by Approximate Nearest Neighbor Search

LanguageJapanese
TypeProceedings of Japanese Conferences
AuthorsKazuto Noguchi, Tomohiro Nakai, Koichi Kise, Masakazu Iwamura
TitleHigh Speed and Small Memory Object Recognition by Approximate Nearest Neighbor Search
Journal第13回画像センシングシンポジウム(SSII07)予稿集
Presentation numberIN2-23
ReviewedNot reviewed
DateJune 2007
Research fieldsPattern recognition, Object Recognition
KeyNoguchi2007_SSII (id=984)

Abstract

SIFT 等の画像の局所記述子を用いて,最近傍探索によって物体認識を行う場合には,一画像あたりの特徴ベクトルの数が膨大になるため,探索効率が重要となる.本稿では,「認識のためには大半の最近傍は不要で ある」という観点から,省メモリで高速性をもった認識法を提案する.一万画像のデータベースを用いた実験の結果,処理時間が従来手法であるANN やLSH を近似最近傍探索の手法として用いた場合の約1/10 に削減でき,例えば,認識率98%,処理時間4.5ms/query を達成できることが分かった.

Files

Export this publication

Format definition
Edits apply immediately and stay in effect until you pick a style again or reset. First line is the default; add lines like "book: …" to override per type.
How to write the definition

Insert a field with braces like {authors}. A part enclosed in [ ... ] is omitted entirely when any field inside it is empty. Available fields:

{authors}{authors_and}{authors_ja}{authors_ja_tight}{authors_en}{authors_en_and}{authors_tight}{first_author}{title}{title_ja}{title_en}{journal}{journal_ja}{journal_en}{book_title}{volume}{number}{series}{presen_id}{pages}{pp}{num_pages}{year}{month}{month_en}{month_short}{ym}{date}{date_ja}{date_en}{publisher}{address}{location}{review}{review_ja}{review_en}{reviewed_mark}{presen_type}{type}{type_label}{doi}{url}{key}{awards}

← Back to list