{"id":"W4200106304","doi":"10.1109/ictc52510.2021.9620801","title":"Robust Inspection of Micro-LED Chip Defects Using Unsupervised Anomaly Detection","year":2021,"lang":"en","type":"article","venue":"2021 International Conference on Information and Communication Technology Convergence (ICTC)","topic":"Industrial Vision Systems and Defect Detection","field":"Engineering","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Information Technology Research Centre; Ministry of Science and ICT, South Korea; Ministry of Trade, Industry and Energy","keywords":"Autoencoder; Anomaly detection; Computer science; Artificial intelligence; Deep learning; Convolutional neural network; Pattern recognition (psychology); Process (computing); Unsupervised learning; Ground truth; Machine learning","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000544894,0.0007233422,0.0006686469,0.0009636823,0.0001597217,0.000399226,0.000829089,0.0005579154,0.000298606],"category_scores_gemma":[0.00154634,0.0001686423,0.000521113,0.0004485003,0.000339415,0.0006105027,0.0006205649,0.0006080107,0.0002609573],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003074867,"about_ca_system_score_gemma":0.0004680525,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001809804,"about_ca_topic_score_gemma":0.003005107,"domain_scores_codex":[0.9993402,0.00008548574,0.00002840759,0.0002168265,0.0002581374,0.00007097344],"domain_scores_gemma":[0.9988123,0.0003014325,0.0002114669,0.0001955844,0.0004335589,0.00004564895],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004203374,0.0004534097,0.02224272,0.0002463213,0.0001852801,0.000214477,0.0001154851,0.07803085,0.167072,0.0009981608,0.004280641,0.7257404],"study_design_scores_gemma":[0.00001551126,0.0001666703,0.01014252,0.00001222299,0.00003282769,0.0002926092,0.00003462226,0.8967426,0.09037497,0.0008252623,0.001338921,0.0000212165],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3258825,0.0008617738,0.6639352,0.0001764081,0.00008438079,0.0001011378,0.0003150866,0.006908812,0.001734661],"genre_scores_gemma":[0.846973,0.0002977196,0.1492717,0.0001033675,0.00002984324,0.00004777057,0.001085756,0.0001406325,0.00205026],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001809804,"threshold_uncertainty_score":0.003598511,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03552251364881482,"score_gpt":0.24223021881004,"score_spread":0.2067077051612252,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}