CAJ | 학술논문

针对国内人工药品检测的低效率、低准确率的不足，文章介绍了一套根据国家行业标准设计的基于智能机器视觉的可见异物自动化检测系统。该系统主要包括机械传动模块、电气控制模块、图像识别与处理模块。根据异物运动连续性和噪声运动无序性等特点，提出了改进的三次差分和能量累积算法来提取运动杂质，然后采用基于基于SIFT特征匹配和最邻近匹配的目标跟踪算法对杂质进行跟踪，获取杂质的大小和数目并分析出杂质总类，最后检测出杂质情况。最后把检测结果与国家标准进行比对，判断出该药剂是否合格。测试表明，系统的检测准确率达90％以上，满足企业要求，基本能替代人工检测。
침대국내인공약품검측적저효솔、저준학솔적불족，문장개소료일투근거국가행업표준설계적기우지능궤기시각적가견이물자동화검측계통。해계통주요포괄궤계전동모괴、전기공제모괴、도상식별여처리모괴。근거이물운동련속성화조성운동무서성등특점，제출료개진적삼차차분화능량루적산법래제취운동잡질，연후채용기우기우SIFT특정필배화최린근필배적목표근종산법대잡질진행근종，획취잡질적대소화수목병분석출잡질총류，최후검측출잡질정황。최후파검측결과여국가표준진행비대，판단출해약제시부합격。측시표명，계통적검측준학솔체90％이상，만족기업요구，기본능체대인공검측。
According to the national standards of production,our team design a automatic impurity detecting system based on intelligent visual technology, against the low efficiency and low accuracy of domestic artificial detection. The system mainly includes mechanical transmission module, electrical control system module and image processing module. According to the feature：continuity of impurities movement and discontinuity of noise movement, using the third difference with the energy accumulation algorithm detects particles, then use the SIFT features and MeanShifi algorithm to track impurities, finally detect the extracted impurities, and find out whether the product is qualified. Experimental results show that the system accuracy rate can reach 90%. It has meet requirements of most enterprise, and in most cases can replace the original manual testing.