Detection of Broken Pharmaceutical Drugs using Enhanced Feature Extraction Technique

摘要

Medication has become more important in everyone?s life; people are affected by many diseases. There are certain diseases which cannot be cured without medication. The production of medicine has increased a lot in recent days. During production there may be damages like breakage, cracks present in the tablets or capsules. Consumption of these damaged tablets may cause some problem in skin, eyes and mouth. Most of the tablets are not advisable to be consumed in broken form. Manual inspection is a very challenging task. Image processing plays a major role in automation of visual inspection. Therefore we propose some ideas to identify the damaged tablets after production. This is a series of process involving image enhancement, segmentation, thresholding, filtration, pixel calculation, subtraction, de-noising and region based statistic to identify the broken tablets. In the case of capsules we propose a feature extraction technique to find the defective blister.