Enhancing classification in correlative microscopy using multiple classifier systems with dynamic selection

Bitrus, Samuel; Fitzek, Harald Matthias; Rigger, Eugen; Rattenberger, Johannes; Entner, Doris

doi:10.1016/j.ultramic.2022.113567

Cited by 1 publication

(2 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Various classifiers have been reported in the literature to which texture spectra are applied as a multidimensional characteristic vector [13][14][15][16][17][18][19][20]. In particular, in references [12,14], a multi-class classifier based on image statistics is described, applied, and optimized.…”

Section: Applicationmentioning

confidence: 99%

“…The histogram h(k) has R K dimensions, where the value of K is the maximum texture unit value. Now, since the objective is to apply to the histogram h(k) in image classification, it is interpreted as a texture spectrum and then is used as a characteristic vector in supervised (multi-class and one-class) and unsupervised (clustering) classifiers [10,[13][14][15][16][17]. Such classification systems operate in real time and efficiently [18][19][20]; when the spectrum h(k) has low dimensional space, the histogram contains a sufficient amount of texture information of the image under study, the classifier is optimized, and the electronic device is task-specific.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A New Texture Spectrum Based on Parallel Encoded Texture Unit and Its Application on Image Classification: A Potential Prospect for Vision Sensing

Guillen Bonilla,

Franco Rodríguez,

Guillen Bonilla

et al. 2023

Sensors

View full text Add to dashboard Cite

In industrial applications based on texture classification, efficient and fast classifiers are extremely useful for quality control of industrial processes. The classifier of texture images has to satisfy two requirements: It must be efficient and fast. In this work, a texture unit is coded in parallel, and using observation windows larger than 3×3, a new texture spectrum called Texture Spectrum based on the Parallel Encoded Texture Unit (TS_PETU) is proposed, calculated, and used as a characteristic vector in a multi-class classifier, and then two image databases are classified. The first database contains images from the company Interceramic®® and the images were acquired under controlled conditions, and the second database contains tree stems and the images were acquired in natural environments. Based on our experimental results, the TS_PETU satisfied both requirements (efficiency and speed), was developed for binary images, and had high efficiency, and its compute time could be reduced by applying parallel coding concepts. The classification efficiency increased by using larger observational windows, and this one was selected based on the window size. Since the TS_PETU had high efficiency for Interceramic®® tile classification, we consider that the proposed technique has significant industrial applications.

show abstract