Harness machine vision to inspect products, detect dirt or contaminants.

Scientists at the USDA-ARS Instrumentation and Sensing Laboratory are developing machine vision systems that can detect contamination the human eye often can't see. To quickly identify fecal contamination or contaminants that should not be in a product, engineers are building a prototype multispectral imaging apple-inspection system. It uses the reflectance from apples in the invisible near-infrared and visible color light bands, as well as fluorescence techniques, to detect dirt, fly specks, fungi, rot and other diseases that can cause illness or negatively impact quality. The system can potentially be used on other products as well.

These machine vision systems are quicker and more accurate than the human eye and don't require anyone to handle product. The research team is testing machine vision on a commercial apple-sorting line. The researchers are using a new digital spectral camera that can take pictures at different wavelengths simultaneously, creating multiple images. Some wavelengths are chosen because of their identifiable relationships to photosynthetic pigments in apples, the test product.

Engineers added a fluorescence capability to the lab's existing hyperspectral imaging equipment. The instrument, designed and hand-built by the team using commercially available components, can capture images at up to 256 different wavelengths. In their research, the scientists choose a few optimal spectral bands from many that will get the job done with enough speed and accuracy when used in multispectral imaging systems. Imaging systems can scan a whole object in a fraction of a second and are more suitable for real-time use in processing plants.

This latest imaging system has the newest imaging spectrograph and halogen and fluorescent lamps, all packaged in one unit that sits above a motorized positioning table where product is placed. For reflectance sensing, visible to near-infrared light comes from quartz halogen bulbs connected to the unit through fiber-optic lines, while fluorescence imaging uses fluorescent lamps. ARS-developed software analyzes the hyperspectral images.

The imaging spectrograph scans a moving apple hundreds of times, each time sensing a line across the apple's surface. The light on each point on the line is spread out like a rainbow by the spectrograph, creating a three-dimensional image. Mathematical algorithms interpret the multiple images.

The lab has a cooperative research and development agreement (CRADA) with Stork Gamco Inc., Gainesville, GA, to commercialize the system and move it into use in poultry processing plants. Stork Gamco will soon test the system in a chicken-processing plant on lines that move 140 birds a minute. The system could handle up to 180 birds a minute. The processing industry is moving to high-speed lines and wants the highest feasible speeds for maximum efficiency. It sees machine vision as the way to make it possible while also improving inspection efficacy.

Further information. Yud-Ren Chen, USDA-ARS Agricultural Engineering, Beltsville Engineering Center, Room 001A, 10300 Baltimore Blvd., Beltsville, MD 20705; phone: [phone]; fax: [phone]; email: [e-mail].