Bibliographic record
Abstract
Machine vision system has been fostered to solve many realistic problems in various fields. Its role in achieving superior quality and productivity is of paramount importance. But, for such system to be attractive, it needs to be fast, accurate and cost-effective. This dissertation is based on a number of practical machine vision based inspection projects obtained from the automotive industry. It presents a collection of developed efficient fuzzy machine vision approaches endorsed with experimental results. It also covers the conceptual design, development and testing of various fuzzy machine vision based inspection approaches for different industrial applications. To assist in developing and evaluating the performance of the proposed approaches, several parts are tested under varying lighting conditions. This research deals with two important aspects of machine vision based inspection. In the first part, it concentrates on the topics of component detection and component orientation identification. The components used in this part are metal clips mounted on a dash panel frame that is installed in the door of trucks. Therefore, we propose a fuzzy machine vision based clip detection model and a fuzzy machine vision based clip orientation identification model to inspect the proper placement of clips on dash panels. Both models are efficient and fast in terms of accuracy and processing time. In the second part of the research, we are dealing with machined part defects such as broken edge, porosity and tool marks. The se defects occur on the surface of die cast aluminum automotive pump housings. As a result, an automated fuzzy machine vision based broken edge detection method, an efficient fuzzy machine vision based porosity detection technique and a neuro-fuzzy part classification model based on tool marks are developed. Computational results show that the proposed approaches are effective in yielding satisfactory results to the tested image databases. There are four main contributions to this work. The first contribution is the development of the concept of composite matrices in conjunction with XOR feature extractor using fuzzy subtractive clustering for clip detection. The second contribution is about a proposed model based on grouping and counting pixels in pre-selective areas which tracks pixel colors in separated RGB channels to determine whether the orientation of the clip is acceptable or not. The construction of three novel edge based features embedded in fuzzy C-means clustering for broken edge detection marks the third contribution. At last, the fourth contribution presents the core of porosity candidates concept and its correlation with twelve developed matrices. This, in turn, results in the development of five different features used in our fuzzy machine vision based porosity detection approach.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.010 | 0.003 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".