PICTURE PROCESSING SYSTEM, PICTURE PROCESSING METHOD, AND PICTURE PROCESSING PROGRAM

• Main Authors: HISAKU AKIYOSHI, NAGATA TAKESHI, MAEKAWA HIDEMASA, MASAMUNE MASARU
• Format: Patent
• Language: English; Japanese
• Published: 12.04.2018
• Subjects: CALCULATING; COMPUTING; COUNTING; ELECTRIC COMMUNICATION TECHNIQUE; ELECTRICITY; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS; PICTORIAL COMMUNICATION, e.g. TELEVISION

PROBLEM TO BE SOLVED: To provide a picture processing system, picture processing method, and picture processing program, for efficiently and unerringly predicting an imaging condition on the basis of an imaged picture.SOLUTION: A picture processor 20 comprises: a learning processing unit 213 that creates row vectors on the basis of picture information on two-dimensional pictures obtained by imaging a subject under a plurality of imaging conditions and the imaging conditions, creates a first matrix obtained by arranging the row vectors of the respective conditions in a column shape, creates a second matrix obtained by arranging the first matrix's orthogonal bases in a column shape in the decreasing order of a contribution ratio, and creates a third matrix obtained by orthogonalizing the second matrix's front half part on the pictures and a fourth matrix obtained by expressing the second matrix's rear half part using an orthogonalization coefficient used for the orthogonalization; and a prediction processing unit 214 that acquires an imaged picture obtained by imaging the subject, calculates a prediction coefficient using the picture information on the two-dimensional pictures and the third matrix, and predicts an imaging condition using the prediction coefficient and the fourth matrix.SELECTED DRAWING: Figure 1 【課題】撮影画像に基づいて、効率的かつ的確に撮影条件を予測するための画像処理システム、画像処理方法及び画像処理プログラムを提供する。【解決手段】画像処理装置２０は、被写体を複数の撮影条件で撮影した２次元画像の画像情報と撮影条件とに基づいて行ベクトルを生成し、撮影条件毎の行ベクトルを列状に並べた第１行列を生成し、第１行列において、寄与率の高い順番に直交基底を列状に並べた第２行列を生成し、第２行列の画像に関する前半部分を直交化した第３行列と、直交化に用いた直交化係数により、前記第２行列の後半部分を表現した第４行列を生成する学習処理部２１３と、被写体を撮影した撮影画像を取得し、２次元画像の画像情報と第３行列とを用いて予測係数を算出し、予測係数と第４行列とを用いて撮影条件を予測する予測処理部２１４とを備える。【選択図】図１