PROBLEM TO BE SOLVED: To provide an image processor or the like capable of identifying an abnormality of a fine structure of an inspection object surface with high accuracy even in the case that a contour edge exists in an inspection object, such as a mucous membrane in an intraluminal image.SOLUTION: An image processor 1 includes a contour edge area extraction part 110 for extracting a contour edge area of an inspection object from an image obtained by imaging the inside of a lumen of a living body, an inspection area setting part 120 for setting an inspection area in the image so as not to include the contour edge area, and an abnormal structure identification part 130 for identifying whether a fine structure of the surface of the inspection object is abnormal on the basis of texture information of the inspection area.COPYRIGHT: (C)2014,JPO&INPIT【課題】管腔内画像内に粘膜等の検査対象に輪郭エッジが存在する場合においても、検査対象表面の微細構造の異常を精度良く識別できる画像処理装置等を提供する。【解決手段】画像処理装置1は、生体の管腔内を撮像した画像から、検査対象の輪郭エッジ領域を抽出する輪郭エッジ領域抽出部110と、上記画像内に、輪郭エッジ領域を内包しないように検査領域を設定する検査領域設定部120と、該検査領域のテクスチャ情報を基に、検査対象の表面の微細構造が異常であるか否かを識別する異常構造識別部130とを備える。【選択図】図1
