Implementing Fine Particle Recognition Based on the ITTI Visual Saliency Model
Abstract
filtering is adopted to perform denoising processing on particle images, Subsequently, ITTI model is used to extract low-level visual features
such as intensity, color and orientation, construct Gaussian pyramids to generate multi-scale feature spaces, and apply center- surround difference mechanism to generate saliency maps, thereby achieving adaptive enhancement of particle regions, Then, through threshold segmentation and morphological processing, particle extraction and recognition are completed. Experimental results show that the ITTI visual saliency
model can effectively highlight edge and contour features of particles, while reducing the missed detection of small particles by traditional
preprocessing methods, and improving the recognition accuracy and robustness of particles. This method provides an effective technical approach to detecting particle targets in complex backgrounds, with strong practical value.
Keywords
Full Text:
PDFReferences
[1] Villafañe L, Aliseda A, Ceccio S, et al. 50 Years of International Journal of Multiphase Flow: Experimental methods for dispersed multiphase flows[J]. International Journal of Multiphase Flow, 2025, 189: 105239.
[2] Venkat S N, Ciardi T G, Lu M. A General Materials Data Science Framework for Quantitative 2D Analysis of Particle Growth from Image Sequences[J]. Integrating Materials and Manufacturing Innovation, 2024(1): 13.
[3] Zhang Yujin. China Image Engineering: 2021[J]. China Journal of Image and Graphics, 2022, 27(04): 1009-1022.
[4] Su Ailiu. Research on Object Detection and Contour Extraction from Heterogeneous Images Based on Visual Saliency [D]. Nanjing
University of Aeronautics and Astronautics, 2015.
[5] Yan Ma, Huan Li. Infrared small target detection in complex background based on visual attention mechanism [J]. Journal of shenyang
ligong university, 2014.
[6] Itti L. A model of saliency-based visual attention for rapid scene analysis[J]. IEEE Trans, 1998, 20.
[7] Fan Yuliang, Walter WANG, Zhang Jiayan. Infrared Ship Detection Algorithm Based on Adaptive Scale Saliency Map Fusion [J]. Radio
Communication Technology, 2022, 48(6): 8.
[8] Liu Zixuan, Glory, Gong Hang. Visual quality analysis of building ground floor space based on visual calculation and eye movement [J].
Journal of Hebei University of Engineering (Natural Science Edition), 2025, 42(5): 104-112.
[9] Song Z, Yang J, Zhang D, et al. Semi-supervised Dim and Small Infrared Ship Detection Network Based on Haar Wavelet[J]. IEEE Access, 2021, PP(99): 1-1.
[10] Barlow H. Possible Principles Underlying the Transformations of Sensory Messages[J]. 2012.
[11] Bonaiuto J J, Itti L. Combining attention and recognition for rapid scene analysis[J]. IEEE, 2005.
[12] Feng Wei, Liu Guangyu, Liu Biao, et al. Sonar image denoising algorithm based on adaptive Wiener filtering and 2D-VMD [J]. Journal
of Nanjing University of Information Science & Technology (Natural Science Edition), 2024, 16(1): 97-105.
[13] Anagnostopoulos C N, Iliou T, Giannoukos I. Features and classifiers for emotion recognition from speech: a survey from 2000 to
2011[J]. Artificial Intelligence Review, 2015, 43(2): 155-177.
[14] Neumann M, Vu N T. Attentive convolutional neural network based speech emotion recognition: a study on the impact of input features,
signal length, and acted speech[C]//Proceedings of the 18th Annual Conference of the International Speech Communication Association
(INTERSPEECH 2017). Stockholm, Sweden: ISCA, 2017: 2362-2366.
[15] Busso C, Bulut M, Lee C C, et al. IEMOCAP: interactive emotional dyadic motion capture database[J]. Language Resources and Evaluation, 2008, 42(4): 335-359.
DOI: http://dx.doi.org/10.70711/aitr.v4i2.9821
Refbacks
- There are currently no refbacks.
