鉗子ロボット操作に向けたLab色空間の色相を用いた内視鏡映像内の術具の画像認識

抄録

A new image processing method using luminance and hue of L*a*b* color space for real time processing and detecting achromatic surgical instrument in endoscopic view has been developed. The proposed method could be used for semi-automatic control of a forceps robot. It makes use of a luminance gamma correction, a masking process based on combination of removal of the halation and the shade using L* axis, the organ’s red color and the fat’s yellow color using a* and b* axes, and the boundary and small area. The area of the surgical instruments recognized in three laparoscopic surgical videos using this method were performed, and the recognition rate was 71 % for the forceps. The average processing time was 14 ms.