Crossing Line Profile: A New Approach to Detecting Defects in Aluminium Die Casting

Mery, Domingo

doi:10.1007/3-540-45103-x_96

Cited by 35 publications

(26 citation statements)

References 7 publications

(14 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Afterwards, each closed region is segmented. In order to identify the potential defects, features are extracted from crossing line profiles of each segmented region [6]. Crossing line profiles are grey level profiles along straight lines crossing each segmented region in the middle.…”

Section: B1) Identification Of Potential Defectsmentioning

confidence: 99%

Automated Multiple View Inspection Based on Uncalibrated Image Sequences

Mery

Carrasco

2005

Image Analysis

Self Cite

View full text Add to dashboard Cite

Abstract. The Automated Multiple View Inspection (AMVI) has been recently developed for automated defect detection of manufactured objects. The approach detects defects by analysing image sequences in two steps. In the first step, potential defects are automatically identified in each image of the sequence. In the second step, the potential defects are tracked in the sequence. The key idea of this strategy is that only the existing defects (and not the false detections) can be successfully tracked in the image sequence because they are located in positions dictated by the motion of the test object. The AMVI strategy was successfully implemented for calibrated image sequences. However, it is not simple to implement it in industrial environments because the calibration process is a difficult task and unstable. In order to avoid the mentioned disadvantages, in this paper we propose a new AMVI strategy based on the tracking of potential detects in uncalibrated image sequences. Our approach tracks the potential defects based on a motion model estimated from the image sequence self. Thus, we obtain a motion model by matching structure points of the images. We show in our experimental results on aluminium die castings that the detection is promising in uncalibrated images by detecting 92.3% of all existing defects with only 0.33 false alarms per image.

show abstract

Section: B1) Identification Of Potential Defectsmentioning

confidence: 99%

Automated Multiple View Inspection Based on Uncalibrated Image Sequences

Mery

Carrasco

2005

Image Analysis

Self Cite

View full text Add to dashboard Cite

show abstract

“…Gray-level profiles along straight lines crossing each region candidate in the middle are extracted. A potential region r is segmented if the profile that contains the most similar gray levels in the extremes fulfills contrast criteria [90]. This approach was used to detect discontinuities in a homogeneous material, e.g., flaws in automotive parts.…”

Section: Parts Detectionmentioning

confidence: 99%

Applications in X-ray Testing

Mery

2015

Computer Vision for X-Ray Testing

Self Cite

View full text Add to dashboard Cite

In this chapter, relevant applications on X-ray testing are described. We cover X-ray testing in (i) castings, (ii) welds, (iii) baggage, (iv) natural products, and (v) others (like cargos and electronic circuits). For each application, the state of the art is presented. Approaches in each application are summarized showing how they use computer vision techniques. A detailed approach is shown in each application and some examples using Matlab are given in order to illustrate the performance of the methods.Cover image: 3D representation of the X-ray image of a wheel (X-ray image C0023_0001 colored with 'sinmap' colormap).

show abstract

“…Features used for classifier training can be separated in five categories: intensity level, crossing line profile [9], geometrical, contrast and texture features. Once the features are extracted a principal component analysis is applied.…”

Section: Description and Classificationmentioning

confidence: 99%

Image Preprocessing Assessment Detecting Low Contrast Regions under Non-homogeneous Light Conditions

Vargas

Molina

Branch

et al. 2014

Image and Video Technology – PSIVT 2013 Workshops

View full text Add to dashboard Cite

Abstract. This paper focuses on evaluating the pre-processing impact in detecting low contrast regions on irregular surfaces with non-homogeneous lighting. Non homogeneous lighting represents an obstacle to the correct segmentation and subsequent classification of relevant image regions. For example in grayscale images, intensity variations are detected on the same region. Therefore lower contrast regions require an adequate sensitivity level at the segmentation stage. Segmentation, description and classification techniques will be applied over a set of images without pre-processing and over the same set of images with pre-processing, in order to achieve the assessment. The images used in this paper were obtained from a visual inspection prototype for flaw detection on dentures. The outcome shows that an appropriate image pre-processing is required to improve the detection process performance for the given circumstances.

show abstract

Crossing Line Profile: A New Approach to Detecting Defects in Aluminium Die Casting

Cited by 35 publications

References 7 publications

Automated Multiple View Inspection Based on Uncalibrated Image Sequences

Automated Multiple View Inspection Based on Uncalibrated Image Sequences

Applications in X-ray Testing

Image Preprocessing Assessment Detecting Low Contrast Regions under Non-homogeneous Light Conditions

Contact Info

Product

Resources

About