Automatic finding of optimal image processing for extracting concrete image cracks using features ACTIT

Bai, Haiying; Yata, Noriko; Nagao, Tomoharu

doi:10.1002/tee.21732

Cited by 4 publications

(4 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous studies have addressed the automated design of sensor locations [ 4 , 5 , 6 , 7 , 8 , 9 , 10 , 11 , 12 ], illumination levels [ 13 , 14 , 15 , 16 , 17 , 18 ], and recognition algorithms [ 19 , 20 , 21 , 22 , 23 , 24 , 25 ]. Some studies proposed a method to automatically determine the place to set a vision sensor for specific features of recognition targets to satisfy the specific constraints of recognition requirements [ 4 , 5 , 6 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automated Field-of-View, Illumination, and Recognition Algorithm Design of a Vision System for Pick-and-Place Considering Colour Information in Illumination and Images

Chen

Ogata

Ueyama

et al. 2018

Sensors

View full text Add to dashboard Cite

Machine vision is playing an increasingly important role in industrial applications, and the automated design of image recognition systems has been a subject of intense research. This study has proposed a system for automatically designing the field-of-view (FOV) of a camera, the illumination strength and the parameters in a recognition algorithm. We formulated the design problem as an optimisation problem and used an experiment based on a hierarchical algorithm to solve it. The evaluation experiments using translucent plastics objects showed that the use of the proposed system resulted in an effective solution with a wide FOV, recognition of all objects and 0.32 mm and 0.4° maximal positional and angular errors when all the RGB (red, green and blue) for illumination and R channel image for recognition were used. Though all the RGB illumination and grey scale images also provided recognition of all the objects, only a narrow FOV was selected. Moreover, full recognition was not achieved by using only G illumination and a grey-scale image. The results showed that the proposed method can automatically design the FOV, illumination and parameters in the recognition algorithm and that tuning all the RGB illumination is desirable even when single-channel or grey-scale images are used for recognition.

show abstract

Section: Introductionmentioning

confidence: 99%

“…Some studies have attempted to automate the image processing procedures. Automated image pre-processing techniques were proposed in [ 19 , 20 , 21 ]. Some other studies investigated the automated design for feature extraction [ 22 , 23 ].…”

Section: Introductionmentioning

confidence: 99%

Automated Field-of-View, Illumination, and Recognition Algorithm Design of a Vision System for Pick-and-Place Considering Colour Information in Illumination and Images

Chen

Ogata

Ueyama

et al. 2018

Sensors

View full text Add to dashboard Cite

show abstract

“…Automated design of image‐recognition algorithms has been studied extensively. Some studies proposed the automated design for preprocessing, including one or more image transformations . Some other studies investigated the automated design for feature extraction and/or the discriminator .…”

Section: Introductionmentioning

confidence: 99%

Automated design of image recognition in capturing environment

Ogata

Yukisawa

Arai

et al. 2017

IEEJ Transactions Elec Engng

View full text Add to dashboard Cite

This study aims at automating the design of the image-recognition algorithm and the image-acquisition environment for an industrial picking system. Here for the image-recognition algorithm, a preprocessing image parameter and a discriminator using local features in images are targeted. For the image-acquisition environment, the camera distance from the target objects and the illumination strength of each RGB color are considered. The problem is formulated as an optimization problem, and a method is proposed to derive solutions using a two-phase random multistart local optimization for the image-acquisition environment and the image-recognition algorithm. In addition, experiment-based optimization is made to deal with the uncertainty of the capturing environment. Furthermore, positions and angles are considered in a robot coordinate system to simplify the image-acquisition process. The three evaluation experiments targeting objects with different surface characteristics are conducted. The results show that the proposed system successfully designed parameter sets for the image-acquisition environment and the image-recognition algorithm that suited the characteristics of the target objects. The object recognition rate, that is, F measure, is 1 for all objects in all the three experiments.

show abstract

“…In [6]- [8], the target task was not object recognition, but image conversion, and the combination of modules was designed by using a genetic algorithm (GA). In [9], [10], the target task was object recognition, and only the preprocessing was designed by using a GA, as it was assumed that feature extraction and recognition were well designed. The study in [11] aimed to design feature extraction, and a method to select adequate features from many candidates was proposed.…”

Section: Introductionmentioning

confidence: 99%

Simultaneous design of image conversion parameters and classifier in object recognition for a picking task

Tsujimoto

Huang

Arai

et al. 2014

2014 IEEE International Conference on Robotics and Biomimetics (ROBIO 2014)

View full text Add to dashboard Cite

In general, it is difficult to construct an object recognition system, because such a system has many design variables and often these cannot be designed independently. However, in certain manufacturing tasks, it is not always necessary to design all variables. In this study, we selected a picking task as the target task for the experiment. We restricted the design variables to parameters of the preprocessing modules and the classifier, and then proposed a method for constructing an object recognition system to achieve the intended task. We formulated the problem as an optimization problem, and proposed to solve it by using nearest neighbor search. In order to demonstrate the efficiency of our method, we conducted experiments on training images under various conditions. By using the obtained parameters and classifier, the system was able to detect all of the target objects in the target images, to recognize the objects' shapes correctly, and to estimate the objects' positions and angles within an error range that is sufficiently small for a picking task. K. Tsujimoto is with

show abstract

Automatic finding of optimal image processing for extracting concrete image cracks using features ACTIT

Cited by 4 publications

References 10 publications

Automated Field-of-View, Illumination, and Recognition Algorithm Design of a Vision System for Pick-and-Place Considering Colour Information in Illumination and Images

Automated Field-of-View, Illumination, and Recognition Algorithm Design of a Vision System for Pick-and-Place Considering Colour Information in Illumination and Images

Automated design of image recognition in capturing environment

Simultaneous design of image conversion parameters and classifier in object recognition for a picking task

Contact Info

Product

Resources

About