IMAGE PROCESSING PROGRAM, IMAGE PROCESSING SYSTEM, AND IMAGE PROCESSING METHOD

To calculate a feature quantity with high robustness.SOLUTION: An arithmetic logical unit 1b converts a first hue value for each pixel in an image 10 to a second hue value calculated by referring a standard hue value Hbase as a standard that is determined based on a distribution state of the first h...

Full description

Saved in:
Bibliographic Details
Main Authors BABA TAKAYUKI, MORIWAKI YASUTAKA, SUGIMURA MASAHIKO, TAKEBE HIROAKI
Format Patent
LanguageEnglish
Japanese
Published 23.05.2019
Subjects
CALCULATING
COMPUTING
COUNTING
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
PHYSICS
Online AccessGet full text

Cover

More Information
Summary:To calculate a feature quantity with high robustness.SOLUTION: An arithmetic logical unit 1b converts a first hue value for each pixel in an image 10 to a second hue value calculated by referring a standard hue value Hbase as a standard that is determined based on a distribution state of the first hue value in the image 10. Then, the arithmetic logical unit 1b calculates a difference of the second hue values among pixels included in image pairs 11a to 11d set in a feature area 11 in the image 10, and calculates a local feature quantity 12 of the feature area 11 having a bit corresponding to each of the image pairs 11a to 11d based on the difference.SELECTED DRAWING: Figure 1 【課題】ロバスト性の高い特徴量を算出する。【解決手段】演算部１ｂは、画像１０の各画素についての第１の色相値を、画像１０における第１の色相値の分布状態に基づいて決定される基準色相値Ｈｂａｓｅを基準として算出された第２の色相値に変換する。そして、演算部１ｂは、画像１０内の特徴領域１１に設定された画素ペア１１ａ〜１１ｄのそれぞれに含まれる画素間における第２の色相値の差分を算出し、差分に基づいて、画素ペア１１ａ〜１１ｄのそれぞれに対応するビットを有する、特徴領域１１についての局所特徴量１２を算出する。【選択図】図１
Bibliography:Application Number: JP20170204706