Wyniki wyszukiwania - BazTech

1

Textural features based on run length encoding in the classification of furniture surfaces with the orange skin defect

Pach Jakub, Chmielewski Leszek J., Orłowski Arkadiusz, Kruk Michał, Kurek Jarosław, Świderski Bartosz, Antoniuk Izabella, Wieczorek Grzegorz, Śmietańska Katarzyna, Górski Jarosław

Machine Graphics and Vision

|

2019

|

Vol. 28, No. 1/4

35--45

EN

Textural features based upon thresholding and run length encoding have been successfully applied to the problem of classification of the quality of lacquered surfaces in furniture exhibiting the surface defect known as orange skin. The set of features for one surface patch consists of 12 real numbers. The classifier used was the one nearest neighbour classifier without feature selection. The classification quality was tested on 808 images 300 by 300 pixels, made under controlled, close-to-tangential lighting, with three classes: good, acceptable and bad, in close to balanced numbers. The classification accuracy was not smaller than 98% when the tested surface was not rotated with respect to the training samples, 97% for rotations up to 20 degrees and 95.5% in the worst case for arbitrary rotations.

2

Context-based segmentation of the longissimus muscle in beef with a deep neural network

Talacha Karol, Świderski Bartosz, Kurek Jarosław, Kruk Michał, Półtorak Andrzej, Chmielewski Leszek J., Wieczorek Grzegorz, Antoniuk Izabella, Pach Jakub, Orłowski Arkadiusz

Machine Graphics and Vision

|

2019

|

Vol. 28, No. 1/4

47--57

EN

The problem of segmenting the cross-section through the longissimus muscle in beef carcasses with computer vision methods was investigated. The available data were 111 images of cross-sections coming from 28 cows (typically four images per cow). Training data were the pixels of the muscles, marked manually. The AlexNet deep convolutional neural network was used as the classifier, and single pixels were the classified objects. Each pixel was presented to the network together with its small circular neighbourhood, and with its context represented by the further neighbourhood, darkened by halving the image intensity. The average classification accuracy was 96%. The accuracy without darkening the context was found to be smaller, with a small but statistically significant difference. The segmentation of the longissimus muscle is the introductory stage for the next steps of assessing the quality of beef for the alimentary purposes.

3

Hough transform for lines with slope defined by a pair of co-primes

Chmielewski Leszek J., Orlowski Arkadiusz

Machine Graphics and Vision

|

2013

|

Vol. 22, No. 1/4

17--25

EN

Data structure and Hough-type algorithm suitable for ﬁnding the lines having the slope exactly speciﬁed by the ratio of small co-prime numbers is proposed. It is suitable for analysing images like the Ulam square in which the points representing prime numbers form such structures as contiguous lines and other regular sequences of points. This analysis is diﬀerent from that in the case of images in which the real-world objects are represented approximately. Until now in the Ulam square the horizontal and vertical sequences, and those inclined by 45 deg were typically analysed. With the proposed method the sequences having slopes represented by such tangents like 1/3, 2/3, 3/4 etc. can be looked for.