Recognizing Induced Emotions With Only One Feature: A Novel Color Histogram-Based System

Mohseni, Seyed Abdolreza; Wu, Hong Ren; Thom, James A.; Bab–Hadiashar, Alireza

doi:10.1109/access.2020.2975174

Cited by 11 publications

(5 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The pixel distribution of an image is presented by the histogram [42]. The eavesdropper may attack the encryption image over a histogram analysis [43].…”

Section: Histogram Analysismentioning

confidence: 99%

Designing a Novel Efficient Substitution-Box by Using a Flower Pollination Algorithm and Chaos System

2022

IJIES

View full text Add to dashboard Cite

Substitution box (S-box) is a crucial component of symmetric cryptosystems and is mostly used in modern cryptographic ciphers to provide strong data sanctuary. The cryptographic strength of an S-box used in a cipher is directly proportional to the data security provided by the cipher. Thus, this study used a novel approach by combining the hybrid chaos (integrated three functions of chaos maps) to generate pseudo-random number generators and metaheuristic techniques based on the flower pollination algorithm (FPA) to develop an acceptable configuration (8 × 8) S-box. Chaotic maps enhance the initial population of FPA to be an appropriate starting point for the FPA. The objective function of the FPA was the nonlinearity score of the S-box. The FPA is used to balance exploration and exploitation operations. The suggested S-box was compared with several references and passed all the security requirements of S-box, including bijection, strict avalanche criteria (SAC), output bits independence criteria (BIC), nonlinearity, histogram, entropy, correlation coefficients, unified average changing intensity (UACI) and number of pixel change rates (NPCR), in addition to the algebraic cryptanalysis test. The proposed approach had an asymptotic computational complexity of O(n2). The nonlinearity property was 107.25. It is considered an effective and acceptable result. Whereas SAC and BIC were 0.498 and 104.7857, respectively. Simultaneously, all results of UACI and NPCR were close to the predicted normal levels 33.2255 and 99.5693, respectively. While the encryption histogram is more uniform than the simple histogram. Finally, the entropy and correlation coefficients scores result of various images were close to eight and zero, respectively. Therefore, the proposed S-box is proven to be strong and resistant to cryptography attacks.

show abstract

“…The pixel distribution of an image is presented by the histogram [42]. The eavesdropper may attack the encryption image over a histogram analysis [43].…”

Section: Histogram Analysismentioning

confidence: 99%

Designing a Novel Efficient Substitution-Box by Using a Flower Pollination Algorithm and Chaos System

2022

IJIES

View full text Add to dashboard Cite

show abstract

“…The histogram [31] displays an image's pixel distribution. The encryption picture may be attacked by the eavesdropper via a histogram analysis [32].…”

Section: Analysis Of Histogrammentioning

confidence: 99%

Using Three-Dimensional Logistic Equations and Glowworm Swarm Optimization Algorithm to Generate S-Box

2022

IJIES

View full text Add to dashboard Cite

A major component of symmetric cryptosystems is the substitution box (S-box), which is primarily utilized in existing cryptographic ciphers to ensure secure data sanctuaries. The cryptographic strength of an S-box used in the encryption directly correlates to the amount of data protection that a cipher offers. This work developed a suitable configuration (8x8) S-box using metaheuristic approaches based on the Glowworm Swarm Optimization (GSO) algorithm and three-dimensional (3D) logistic equations to construct pseudo-random number generators. Chaotic maps boost the initial population of the GSO, making it a suitable place to start. The nonlinearity score of the S-box served as the GSO's objective function. Operations for exploration and exploitation are balanced using the GSO. In comparison to various references, the proposed S-box satisfied all of the S-security box's requirements, including the strict avalanche criterion (SAC), bijection, nonlinearity, output bits independence criteria (BIC), and histogram. The proposed method's nonlinearity property was 107.00. It is regarded as a successful and effective result. BIC and SAC averages were 103.500 and 0.499, respectively. Compared to a simple histogram, the encryption histogram was more uniform. As a result, it has been demonstrated that the suggested S-box is robust and resistant to cryptographic assaults.

show abstract

“…In [15], the authors used SVM to study the performance of color histograms in different color spaces for content based color image classification. Reference [5] examined the performance of a wide range of classifiers in recognizing induced emotions using the color histogram as a single feature, and different numbers of color histogram bins in both RGB and HSV color spaces were considered in the examination. In [16], the red, green, and blue color components of the RGB color model were selected as features to classify the different groups of materials with supervised machine learning algorithms.…”

Section: Related Workmentioning

confidence: 99%

“…In [4], the authors used the k-nearest neighbor (k-NN) classification principle to classify rock images based on color textures. Reference [5] selected color histograms of three channels in both the RGB and HSV (hue, saturation, value) color spaces as a single feature to recognize induced emotions. In [6], wooden boards were classified by a supervised machine learning classifier based on the main color characteristic obtained through the HSV color model and the co-occurrence matrix characteristic.…”

Section: Introductionmentioning

confidence: 99%

Color Classification of Wooden Boards Based on Machine Vision and the Clustering Algorithm

et al. 2020

View full text Add to dashboard Cite

Color classification of wooden boards is helpful to improve the appearance of wooden furniture that is spliced from multiple wooden boards. Due to the similarity of colors among wooden boards, manual color classification is inaccurate and unstable. Thus, supervised learning algorithms can hardly be used in this scenario. Moreover, wooden boards are long, and their images have a high resolution, which may lead to the growth of computational complexity. To overcome these challenges, in this paper, we propose a new mechanism for color classification of wooden boards based on machine vision. The image of the wooden board is preprocessed to subtract irrelevant colors, and the feature vector is extracted based on 3D color histogram to reduce the computational complexity. In the offline clustering, the feature vector sets are partitioned into different clusters through the K-means algorithm. Then, the clustering result can be used in the online classification to classify the new wood image. Furthermore, to process the abnormal images of wooden boards, we propose an improved algorithm with centroid improvement and image filtering. The experimental results verify the effectiveness of the proposed mechanism.

show abstract

Recognizing Induced Emotions With Only One Feature: A Novel Color Histogram-Based System

Cited by 11 publications

References 41 publications

Designing a Novel Efficient Substitution-Box by Using a Flower Pollination Algorithm and Chaos System

Designing a Novel Efficient Substitution-Box by Using a Flower Pollination Algorithm and Chaos System

Using Three-Dimensional Logistic Equations and Glowworm Swarm Optimization Algorithm to Generate S-Box

Color Classification of Wooden Boards Based on Machine Vision and the Clustering Algorithm

Contact Info

Product

Resources

About