1
|
Ambuj, Machavaram R. Neuromorphic computing spiking neural network edge detection model for content based image retrieval. NETWORK (BRISTOL, ENGLAND) 2024:1-31. [PMID: 38708841 DOI: 10.1080/0954898x.2024.2348018] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/08/2023] [Accepted: 04/22/2024] [Indexed: 05/07/2024]
Abstract
In contemporary times, content-based image retrieval (CBIR) techniques have gained widespread acceptance as a means for end-users to discern and extract specific image content from vast repositories. However, it is noteworthy that a substantial majority of CBIR studies continue to rely on linear methodologies such as gradient-based and derivative-based edge detection techniques. This research explores the integration of bioinspired Spiking Neural Network (SNN) based edge detection within CBIR. We introduce an innovative, computationally efficient SNN-based approach designed explicitly for CBIR applications, outperforming existing SNN models by reducing computational overhead by 2.5 times. The proposed SNN-based edge detection approach is seamlessly incorporated into three distinct CBIR techniques, each employing conventional edge detection methodologies including Sobel, Canny, and image derivatives. Rigorous experimentation and evaluations are carried out utilizing the Corel-10k dataset and crop weed dataset, a widely recognized and frequently adopted benchmark dataset in the realm of image analysis. Importantly, our findings underscore the enhanced performance of CBIR methodologies integrating the proposed SNN-based edge detection approach, with an average increase in mean precision values exceeding 3%. This study conclusively demonstrated the utility of our proposed methodology in optimizing feature extraction, thereby establishing its pivotal role in advancing edge centric CBIR approaches.
Collapse
Affiliation(s)
- Ambuj
- Agricultural and Food Engineering Department, Indian Institute of Technology Kharagpur, Kharagpur, West Bengal, India
| | - Rajendra Machavaram
- Agricultural and Food Engineering Department, Indian Institute of Technology Kharagpur, Kharagpur, West Bengal, India
| |
Collapse
|
2
|
Lakhal S, Darmon A, Mastromatteo I, Marsili M, Benzaquen M. Multiscale relevance of natural images. Sci Rep 2023; 13:14879. [PMID: 37689770 PMCID: PMC10492821 DOI: 10.1038/s41598-023-41714-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/02/2023] [Accepted: 08/30/2023] [Indexed: 09/11/2023] Open
Abstract
We use an agnostic information-theoretic approach to investigate the statistical properties of natural images. We introduce the Multiscale Relevance (MSR) measure to assess the robustness of images to compression at all scales. Starting in a controlled environment, we characterize the MSR of synthetic random textures as function of image roughness [Formula: see text] and other relevant parameters. We then extend the analysis to natural images and find striking similarities with critical ([Formula: see text]) random textures. We show that the MSR is more robust and informative of image content than classical methods such as power spectrum analysis. Finally, we confront the MSR to classical measures for the calibration of common procedures such as color mapping and denoising. Overall, the MSR approach appears to be a good candidate for advanced image analysis and image processing, while providing a good level of physical interpretability.
Collapse
Affiliation(s)
- Samy Lakhal
- Chair of Econophysics and Complex Systems, Ecole Polytechnique, 91128, Palaiseau Cedex, France
- LadHyX, UMR CNRS 7646, Ecole Polytechnique, 91128, Palaiseau Cedex, France
- Institut Jean Le Rond d'Alembert, UMR CNRS 7190, Sorbonne Université, 75005, Paris, France
| | | | - Iacopo Mastromatteo
- Chair of Econophysics and Complex Systems, Ecole Polytechnique, 91128, Palaiseau Cedex, France
- Capital Fund Management, 23 Rue de l'Université, 75007, Paris, France
| | - Matteo Marsili
- Quantitative Life Sciences Section, The Abdus Salam International Centre for Theoretical Physics, 34151, Trieste, Italy
| | - Michael Benzaquen
- Chair of Econophysics and Complex Systems, Ecole Polytechnique, 91128, Palaiseau Cedex, France.
- LadHyX, UMR CNRS 7646, Ecole Polytechnique, 91128, Palaiseau Cedex, France.
- Capital Fund Management, 23 Rue de l'Université, 75007, Paris, France.
| |
Collapse
|
3
|
Bio-inspired contour extraction via EM-driven deformable and rotatable directivity-probing mask. Sci Rep 2022; 12:12309. [PMID: 35853914 PMCID: PMC9296603 DOI: 10.1038/s41598-022-16040-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/14/2021] [Accepted: 07/04/2022] [Indexed: 11/08/2022] Open
Abstract
This paper presents a novel bio-inspired edge-oriented approach to perceptual contour extraction. Our method does not rely on segmentation and can unsupervised learn to identify edge points that are readily grouped, without invoking any connecting mechanism, into object boundaries as perceived by human. This goal is achieved by using a dynamic mask to statistically assess the inter-edge relations and probe the principal direction that acts as an edge-grouping cue. The novelty of this work is that the mask, centered at a target pixel and driven by EM algorithm, can iteratively deform and rotate until it covers pixels that best fit the Bayesian likelihood of the binary class w.r.t a target pixel. By creating an effect of enlarging receptive field, contiguous edges of the same object can be identified while suppressing noise and textures, the resulting contour is in good agreement with gestalt laws of continuity, similarity and proximity. All theoretical derivations and parameters updates are conducted under the framework of EM-based Bayesian inference. Issues of stability and parameter uncertainty are addressed. Both qualitative and quantitative comparison with existing approaches proves the superiority of the proposed method in terms of tracking curved contours, noises/texture resilience, and detection of low-contrast contours.
Collapse
|
4
|
İncetaş MO. Anisotropic Diffusion Filter Based on Spiking Neural Network Model. ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING 2022. [DOI: 10.1007/s13369-021-06404-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/28/2022]
|
5
|
Mingels C, Sachpekidis C, Bohn KP, Hünermund JN, Schepers R, Fech V, Prenosil G, Rominger A, Afshar-Oromieh A, Alberts I. The influence of colour scale in lesion detection and patient-based sensitivity in [68Ga]Ga-PSMA-PET/CT. Nucl Med Commun 2021; 42:495-502. [PMID: 33481506 DOI: 10.1097/mnm.0000000000001364] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/25/2022]
Abstract
OBJECTIVE To investigate the influence of colour scales on the interpretation of [68Ga]Ga-PSMA-11 PET/CT for the diagnosis of recurrent prostate cancer. METHODS 50 consecutive patients who underwent [68Ga]Ga-PSMA-11 PET/CT for recurrent prostate cancer were selected for this retrospective study. The scans were randomised, anonymised and read by five different readers first in the visually nonlinear colour scale 'PET-rainbow'. Scans were then rerandomised and read in the visually linear colour scale 'hot-metal new'. For each scan in each colour scale the numbers of pathological, equivocal and benign lesions were noted. Scans where the majority of readers (≥3) reported at least one PET-positive lesion were recorded as 'pathological'. Patient-level sensitivity was obtained by composite standard with 14.8 ± 1.2 months of follow-up. RESULTS Increased numbers of lesions per patient were reported for all readers in PET-rainbow compared to hot-metal new (37.4 ± 15.2 vs. 33.9 ± 16.4, respectively, P = 0.0005). On a per-patient basis, 43 scans were rated pathological in PET-rainbow, compared to 39 in hot-metal new. Follow-up was available for 30 patients confirming 26 pathological scans with positive follow-up in PET-rainbow, and 23 in hot-metal new. Three pathological scans were missed in hot-metal new. Patient-level sensitivity was higher for PET-rainbow (0.96) compared to hot-metal new (0.85). Inter-reader reliability was higher for hot-metal new (Fleiss κ = 0.76) compared to PET-rainbow (Fleiss κ = 0.60). CONCLUSION Use of PET-rainbow was associated with improved lesion detection and sensitivity compared to hot-metal new, although at cost of reduced inter-rater agreement. Consequently, the use of PET-rainbow for clinical routine and future studies involving [68Ga]Ga-PSMA-11 is recommended.
Collapse
Affiliation(s)
- Clemens Mingels
- Department of Nuclear Medicine, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland
| | | | | | | | | | | | | | | | | | | |
Collapse
|
6
|
Lerer A, Supèr H, Keil MS. Dynamic decorrelation as a unifying principle for explaining a broad range of brightness phenomena. PLoS Comput Biol 2021; 17:e1007907. [PMID: 33901165 PMCID: PMC8102013 DOI: 10.1371/journal.pcbi.1007907] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/18/2020] [Revised: 05/06/2021] [Accepted: 04/06/2021] [Indexed: 11/29/2022] Open
Abstract
The visual system is highly sensitive to spatial context for encoding luminance patterns. Context sensitivity inspired the proposal of many neural mechanisms for explaining the perception of luminance (brightness). Here we propose a novel computational model for estimating the brightness of many visual illusions. We hypothesize that many aspects of brightness can be explained by a dynamic filtering process that reduces the redundancy in edge representations on the one hand, while non-redundant activity is enhanced on the other. The dynamic filter is learned for each input image and implements context sensitivity. Dynamic filtering is applied to the responses of (model) complex cells in order to build a gain control map. The gain control map then acts on simple cell responses before they are used to create a brightness map via activity propagation. Our approach is successful in predicting many challenging visual illusions, including contrast effects, assimilation, and reverse contrast with the same set of model parameters.
Collapse
Affiliation(s)
- Alejandro Lerer
- Departament de Cognició, Desenvolupament i Psicologia de l’Educació, Faculty of Psychology, University of Barcelona, Barcelona, Spain
| | - Hans Supèr
- Departament de Cognició, Desenvolupament i Psicologia de l’Educació, Faculty of Psychology, University of Barcelona, Barcelona, Spain
- Institut de Neurociències, Universitat de Barcelona, Barcelona, Spain
- Institut de Recerca Pediàtrica Hospital Sant Joan de Déu, Barcelona, Spain
- Catalan Institute for Advanced Studies (ICREA), Barcelona, Spain
| | - Matthias S. Keil
- Departament de Cognició, Desenvolupament i Psicologia de l’Educació, Faculty of Psychology, University of Barcelona, Barcelona, Spain
- Institut de Neurociències, Universitat de Barcelona, Barcelona, Spain
| |
Collapse
|
7
|
Lerer A, Supèr H, Keil MS. Luminance gradients and non-gradients as a cue for distinguishing reflectance and illumination in achromatic images: A computational approach. Neural Netw 2018; 110:66-81. [PMID: 30496916 DOI: 10.1016/j.neunet.2018.11.001] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/16/2018] [Revised: 10/26/2018] [Accepted: 11/04/2018] [Indexed: 11/28/2022]
Abstract
The brain analyses the visual world through the luminance patterns that reach the retina. Formally, luminance (as measured by the retina) is the product of illumination and reflectance. Whereas illumination is highly variable, reflectance is a physical property that characterizes each object surface. Due to memory constraints, it seems plausible that the visual system suppresses illumination patterns before object recognition takes place. Since many combinations of reflectance and illumination can give rise to identical luminance values, finding the correct reflectance value of a surface is an ill-posed problem, and it is still an open question how it is solved by the brain. Here we propose a computational approach that first learns filter kernels ("receptive fields") for slow and fast variations in luminance, respectively, from achromatic real-world images. Distinguishing between luminance gradients (slow variations) and non-gradients (fast variations) could serve to constrain the mentioned ill-posed problem. The second stage of our approach successfully segregates luminance gradients and non-gradients from real-world images. Our approach furthermore predicts that visual illusions that contain luminance gradients (such as Adelson's checker-shadow display or grating induction) may occur as a consequence of this segregation process.
Collapse
Affiliation(s)
- Alejandro Lerer
- Departament de Cognició, Desenvolupament i Psicologia de ĺEducació, Faculty of Psychology, University of Barcelona, Barcelona, Spain.
| | - Hans Supèr
- Departament de Cognició, Desenvolupament i Psicologia de ĺEducació, Faculty of Psychology, University of Barcelona, Barcelona, Spain; Institut de Neurociéncies, Universitat de Barcelona, Barcelona, Spain; Institut de Recerca Pediàtrica Hospital Sant Joan de Déu, Barcelona, Spain; Catalan Institute for Advanced Studies (ICREA), Barcelona, Spain
| | - Matthias S Keil
- Departament de Cognició, Desenvolupament i Psicologia de ĺEducació, Faculty of Psychology, University of Barcelona, Barcelona, Spain; Institut de Neurociéncies, Universitat de Barcelona, Barcelona, Spain
| |
Collapse
|
8
|
Bakshi A, Ghosh K. Some insights into why the perception of Mach bands is strong for luminance ramps and weak or vanishing for luminance steps. Perception 2012; 41:1403-8. [PMID: 23513626 DOI: 10.1068/p7358] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/27/2022]
Abstract
In this paper we present some demonstrations concerning the width of Mach bands and henceforth hypothesize certain relations. We show that it is the variation in width of Mach bands in relation to luminance gradients which is responsible for Mach bands being strong for luminance ramps and weak or vanishing for luminance steps. We present the results of the experiments carried out by us using some of these demonstrations to provide support for our claims.
Collapse
Affiliation(s)
- Ashish Bakshi
- Machine Intelligence Unit, Indian Statistical Institute, 203 BT Road, Kolkata-108, India
| | | |
Collapse
|
9
|
Ben-Shahar O, Zucker S. General Geometric Good Continuation: From Taylor to Laplace via Level Sets. Int J Comput Vis 2009. [DOI: 10.1007/s11263-009-0255-8] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/24/2022]
|
10
|
Keil MS. Gradient representations and the perception of luminosity. Vision Res 2007; 47:3360-72. [PMID: 17998141 DOI: 10.1016/j.visres.2007.09.018] [Citation(s) in RCA: 6] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/05/2007] [Revised: 09/19/2007] [Accepted: 09/24/2007] [Indexed: 10/22/2022]
Abstract
The neuronal mechanisms that serve to distinguish between light emitting and light reflecting objects are largely unknown. It has been suggested that luminosity perception implements a separate pathway in the visual system, such that luminosity constitutes an independent perceptual feature. Recently, a psychophysical study was conducted to address the question whether luminosity has a feature status or not. However, the results of this study lend support to the hypothesis that luminance gradients are instead a perceptual feature. Here, I show how the perception of luminosity can emerge from a previously proposed neuronal architecture for generating representations of luminance gradients.
Collapse
Affiliation(s)
- Matthias S Keil
- Basic Psychology Department, Faculty for Psychology, University of Barcelona, Passeig de la Vall d'Hebron 171, E-08035 Barcelona, Spain.
| |
Collapse
|