Detection of Defects on Silicon Wafers

The task is to detect silicon wafers and classify their type depending on defects. This is a multi-class Object Detection task where classes are “good”, “small defect” and “big defect”.

Dataset:

The dataset contains 70 original images that mostly contain defective silicon wafers and 64 augmented images that only contain good silicon wafers. There are 3 types of silicon wafers, all annotated in LabelMe format where, as depicted below.

Data Loading & Annotation:

You have 2 options:

Download data annotated with LabelMe format. Load the imageset and the annotations that you downloaded using ReliUI. Import the imageset using “Import Data” and the annotation file per image folder using the “Import Annotated Dataset” (with the LabelMe annotation format option). Your annotated dataset will be available in the gallery.
Load the raw imageset and annotate the data yourself in any industry standard format you like using the ReliUI’s intuitive annotation functions. Download the image folder. Follow the ReliVision Knowledge Hub User Guide (ReliUI: Data Curation) to define the target state/label (which is the label of the silicon wafer as good, small defect or big defect) to annotate the defects (using rectangle annotation tool as the task is object detection) and to save them in an appropriate industry standard format (for which LabelMe is a good option). A sample annotation of an image, where good, small defect and big defect silicon wafers are shown in green, red and yellow boxes, is as follows:

Silicon Wafer Defect Detection Model Training:

Follow the ReliVision Knowledge Hub User Guide (ReliTrainer: Training an AI Block) to train your AI model for silicon wafer defect detection. The main steps, detailed in the User Guide, include

Model type selection: Object Detection
Annotated dataset selection
Automated or manual train/test split which essentially spares some data for training validation purposes.
Hyper parameter setting: We have chosen the following in this use case:

Epochs: 500
X-Y Resolution: 640 (default)
Learning Rate: 0.01 (default)
Momentum: 0.937 (default)
Weight Decay: 0.005 (default)

Training and Validation loss and mAP curves as a function of epochs.

Building and Running the Pipeline:

Use the pipeline editor to build your pipeline by dragging and dropping the AI/Basic blocks. You will need to select an input data source (your raw image set) and a a classification AI Block connected in series as depicted below. Follow the ReliVision Knowledge Hub User Guide (ReliTrainer: Pipeline Editor / AI Pipeline).

Simply run your pipeline using the execute button at the top. You can review your results using the ReliUI data annotation interface. Your pipeline’s outputs will be saved as a separate set of annotations for each image it is run on. Visit the ReliVision Knowledge Hub User Guide (ReliTrainer: Pipeline Editor / AI Pipeline) for more details. Here is an output example:

Try it by yourself.
Download ReliVision now!

AI Model Train / Test

AI powered solution design-train/test-build functions of the ReliVision are performed in the ReliVision's Training Server [ReliTrainer] which is accessible through the user-friendly ReliUI application. You can train detection, segmentation and classification models, test your models, build complex visual analytics pipelines using your trained AI blocks (AI models) together with Basic blocks (Digital signal/image processing - DSP/DIP - functions).

Refer to ReliTrainer user guide for further details. AI Model Train/Test functions are available with a licensed ReliTrainer.

Deployment

AI powered visual analytics solutions that are built, trained and tested, can be deployed to ReliAudit through the user friendly ReliUI interface. The deployed solutions are run, managed and monitored at the edge by the ReliAudit. The user feedback received from the ReliAudit can also be pulled back to ReliTrainer via ReliUI for retraining.

Refer to ReliAudit user guide for further details. Deployment functions are available with a licensed ReliAudit.