The image processing apparatus sets a specific candidate region extraction unit that extracts a specific candidate region that satisfies a predetermined condition from a biological lumen image obtained by imaging a biological lumen, and a reference region that includes at least a part of the specific candidate region. A reference region setting unit； a local region extracting unit that extracts a local region based on the reference region； a local feature amount calculating unit that calculates a local feature amount that is a feature amount of the local region； and a local region based on the specific candidate region A weight setting unit that sets a weight according to the area； and a feature amount integration unit that integrates local feature amounts.画像処理装置は、生体内管腔を撮像した生体内管腔画像から所定の条件を満たす特定候補領域を抽出する特定候補領域抽出手段と、特定候補領域の少なくとも一部を含む基準領域を設定する基準領域設定手段と、基準領域に基づいて局所領域を抽出する局所領域抽出手段と、局所領域の特徴量である局所特徴量を算出する局所特徴量算出手段と、特定候補領域に基づいて、局所領域に応じた重みを設定する重み設定手段と、局所特徴量を統合する特徴量統合手段と、を備える。
