An Automated Grading/Feedback System for 3-View Engineering Drawings using RANSAC

Kwon, Youngwook Paul; McMains, Sara

doi:10.1145/2724660.2724682

Cited by 8 publications

(6 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The drawing in Figure 15 is used to illustrate the evaluation comparison between Kwon and McMains' study 5 and AMCAD. Figure 16(a) shows the algorithm developed by RANSAC method failed to estimate an appropriate transformation for the front view of the solution drawing when the front view of the student's drawing has multiple errors (labeled "A" and "B" in Figure 15(b)).…”

Section: Automated Grading Of First-year Student Cad Work 2013mentioning

confidence: 99%

“…Since 2003, many researchers and educators have developed automated evaluation tools to assess two-dimensional (2D) 1–11 and three-dimensional (3D) 12–18 computer-aided drawing (CAD) assignments. The purpose of using automated evaluation tools is to provide a fair and objective evaluation, quickly, accurately, and consistently, and to eliminate human errors in the evaluation.…”

Section: Introductionmentioning

confidence: 99%

“…Kwon and McMains 5 proposed an automated grading system for native format AutoCAD file (DWG/DXF files). Although the system is translation and scale invariants, the transformation of solution drawing to user drawing may invariably lead to errors.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Artificial intelligence-enabled evaluating for computer-aided drawings (AMCAD)

Jianwu,

Yew,

et al. 2023

International Journal of Mechanical Engineering Education

View full text Add to dashboard Cite

AMCAD ( www.amcad.ai ) is a web-enabled artificial intelligence (AI) system created to auto-evaluate students’ computer-aided drawing (CAD) work assignments and help students in self-directed learning. It compares two engineering drawings and highlights the differences (errors) between the two. The errors are classified into two categories: “Missing Line” errors shown in red and “Erroneous Line” errors in blue. AMCAD works in tandem with all CAD software. It uses computer vision technology to convert PDF drawings to raster subimages, and XOR to evaluate quantitatively the best-matched with best-aligned views. AMCAD, whose AI algorithms and web application were developed in Python, shows the comparison results in two display modes: superimpose and side-by-side. To encourage students in self-directed leaning, instructional videos can be included in each CAD work assignment.

show abstract

Section: Automated Grading Of First-year Student Cad Work 2013mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Artificial intelligence-enabled evaluating for computer-aided drawings (AMCAD)

Jianwu,

Yew,

et al. 2023

International Journal of Mechanical Engineering Education

View full text Add to dashboard Cite

show abstract

“…: Example of grading using RANSAC algorithm [33] One of the basic approaches for developing an automated drawing grading software has been converting the drawing into a code and comparing the code parameters to calculate the differences and errors. Goh, Siti and Rofans used the same approach to propose a grading software [34].…”

Section: Gradementioning

confidence: 99%

CAD Platform Independent Software for Automatic Grading of Technical Drawings

Ingale

Srinivasan

Bairaktarova

2017

Volume 3: 19th International Conference on Advanced Vehicle Technologies; 14th International Conference on Design Education; 10

View full text Add to dashboard Cite

Spatial visualization is the ability of an individual to imagine an object mentally and understand its spatial orientation. There have been multiple works proving that spatial visualization skills can be improved with an appropriate training. Such training warrant a critical place in the undergraduate engineering curricula in many engineering schools as spatial skills are considered vital for students’ success in the technical and design fields [1–4]. Enhanced spatial skills help not only professionals in the engineering field but also everyone in the 21st century environment. Drawing sectional views requires mental manipulation and visual thinking. To enhance students spatial reasoning, one of the authors of this study, conducted a class in spatial visualization. The course-learning goal aimed at improving first-year engineering students’ spatial reasoning through instruction on freehand drawings of sectional view. During the semester, two teaching assistants had to grade more than 500 assignments that consisted of sectional views of mechanical objects. This was a tedious and a time consuming task. Motivated by this experience, this paper proposes a software aiming at automating grading of students’ sectional view drawings. The proposed software will also give live feedback to students while they are working on the drawings. This interactive tool aims to 1) improve the learning experience of first year students, with limited CAD knowledge, and 2) introduce a pedagogical tool that can enhance spatial visualization training.

show abstract

“…They built the application using the random sample consensus (RANSAC) algorithm, estimating the affine transformations between the two individual drawings. 9 RANSAC is an algorithm used to estimate parameters of a mathematical model from a set of data containing outliers. 10 In their work, the submitted file is compared to the solution file by performing various two-dimensional operations on the submitted drawings.…”

Section: Introductionmentioning

confidence: 99%

ViTA: A flexible CAD-tool-independent automatic grading platform for two-dimensional CAD drawings

Younes

Bairaktarova

2020

International Journal of Mechanical Engineering Education

View full text Add to dashboard Cite

Grading engineering drawings takes a significant amount of an instructor’s time, especially in large classrooms. In many cases, teaching assistants help with grading, adding levels of inconsistency and unfairness. To help in grading automation of CAD drawings, this paper introduces a novel tool that can completely automate the grading process after students submit their work. The introduced tool, called Virtual Teaching Assistant (ViTA), is a CAD-tool-independent platform that can work with exported drawings originating from different CAD software having different export settings. Using computer vision techniques applied to exported images of the drawings, ViTA can not only recognize whether or not a two-dimensional (2 D) drawing is correct, but also offers the detection of many important orthographic and sectional view mistakes such as mistakes in structural features, outline, hatching, orientation, scale, line thickness, colors, and views. We show ViTA’s accuracy and its relevance in the automated grading of 2 D CAD drawings by evaluating it using 500 student drawings created with three different CAD software.

show abstract

An Automated Grading/Feedback System for 3-View Engineering Drawings using RANSAC

Cited by 8 publications

References 13 publications

Artificial intelligence-enabled evaluating for computer-aided drawings (AMCAD)

Artificial intelligence-enabled evaluating for computer-aided drawings (AMCAD)

CAD Platform Independent Software for Automatic Grading of Technical Drawings

ViTA: A flexible CAD-tool-independent automatic grading platform for two-dimensional CAD drawings

Contact Info

Product

Resources

About