We introduce the Advanced Thin Film Inspection System (ATFIS), a state-of-the-art Automatic Visual Inspection (AVI) system developed by IBM that integrates sophisticated subsystems to inspect advanced multilayer electronic packaging.The image acquisition and "image segmentation" (material discrimination) is based on high-radiance illumination, multiband line scan cameras and the Low-level Image Segmentation Architecture (LISA). LISA employs a decision-theoretic approach that classifies pixels according to a decision function defined over a multidimensional "feature space" (for example, local or global image statistics).The image processing and pattern analysis is based on the Parallel Image Processing System for Inspection (PIPSI) architecture. PIPSI's key features include exploitation of emerging hardware and software technologies; highly programmable to adapt quickly to changing functional requirements; and exploitation of image and operator parallelism, making it highly scalable to meet manufacturing requirements. PIPSI factors the image processing and pattern analysis into an operator pipeline that includes image acquisition, image framing, image segmentation, intraframe pattern analysis and interframe pattern analysis. These operations are handled by different parallel processing pools, each pool containing programmable processors that run independently and asynchronously of one another. The system infrastructure also includes a "system master," "processing pool masters," a "tool control user interface" and a "reference data interface."The pattern analysis algorithm is a synthesis of reference-based comparison and design-rule analysis. First, the image input is partitioned into image frames and image segmentation generates a label image where each pixel is labeled according to material, topology or defect class. Then, in intraframe analysis, "reference objects" (geometric patterns) are registered with the label image, and the object areas are scanned to detect "disparities" (unexpected pixel labels). Object-specific rules merge disparities into "discrepancies" and classify discrepancies according to defect type. The "background" pixels are also scanned and analyzed for defects. Finally, interframe analysis merges object and background defects that span multiple frames and generates a fmal defect report. INTRODUCTIONElectronic packaging technology continues to evolve with advances in manufacturing and increased functional requirements. Circuit pattern geometries are becoming smaller and denser, and more layers and materials are used in multilayer composites. As a result, each substrate is more costly to develop, to mass produce and to replace in the field. Automated Visual Inspection (AVI) plays an important role in meeting demanding manufacturing requirements (which include high yield, long term product reliability, defect detection for repair and product disposition, and defect classification for process control). An AVI system must address these and other challenging, often conflicting and constant...

No abstract

Inspection of complex electronic packages requires discrimination between the various materials used in such packages. Variations in the appearance of these materials and in the equipment's illumination complicates the segmentation process. In addition, some materials have similar reflectance and absorption characteristics. As a result, the segmentation process is. sensitive to small variations in the illumination settings, photoresponse nonuniformity, and contrast fluctuations. In this paper, we present two techniques that reduce these variations: 1) a new method to calibrate and correct the photoresponse characteristics of optical inspection systems, and 2) a method to automatically correct for contrast variations between the inspected packages. This results in a more repetitive appearance of the used packaging materials, which in turn results in improved segmentation performance.The photoresponse correction procedure, models the output of each photosite as a linear function of input illumination and the parameters of the model are measured. The response is corrected Using image processing hardware. Experimental results show that the non-uniformity is corrected to within 1 % of the AID dynamic range which agrees with the error analysis. The contrast adjustment method adjusts the image contrast based on histogram features and is adjusted using vendor and custom developed hardware. The relationship between the two techniques is also discussed.