Novelty Detection for the Inspection of Light-emitting Diodes

We propose novel feature-extraction and classification methods for the automatic visual inspection of manufactured LEDs. The defects are located at the area of the p-electrodes and lead to a malfunction of the LED. Besides the complexity of the defects, low contrast and strong image noise make this problem very challenging.

For the extraction of image characteristic we compute radially-encoded features that measure discontinuities along the p-electrode. Therefore, we propose two different methods: the first method divides the object into several radial segments for which mean and standard deviation are computed and the second method computes mean and standard deviation along different orientations. For both methods we combine the features over several segments or orientations by computing simple measures such as the ratio between maximum and mean or standard deviation.

Since defect-free LEDs are frequent and defective LEDs are rare, we apply and evaluate different novelty-detection methods for classification. Therefore, we use a kernel density estimator, kernel principal component analysis, and a one-class support vector machine. We further compare our results to Pearson’s correlation coefficient, which is evaluated using an artificial reference image.

The combination of one-class support vector machine and radially-encoded segment features yields the best overall performance by far, with a false alarm rate of only 0.13% at a 100% defect detection rate, which means that every defect is detected and only very few defect-free p-electrodes are rejected.

Our inspection system does not only show superior performance, but is also computationally efficient and can therefore be applied to further real-time applications, for example solder joint inspection. Moreover, we believe that novelty detection as used here can be applied to various expert-system applications.