Using association rules as texture features

Rushing, John; Ranganath, Heggere S.; Hinke, Thomas H.; Graves, Sara

doi:10.1109/34.946988

Cited by 41 publications

(18 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, using association rules as texture features gradually becomes a hot spot [8][9][10][11]. Applied to texture classification and image segmentation by Rushing et al [12,13], frequently occurring local intensity variation in textures is used to construct association rules. Their experiment studies have shown that the accuracy rate of texture classification using association rules as texture features is higher than that of other methods using GLCM, GLRL, fractal dimension, MRF, and Gabor filter-based features.…”

Section: Introductionmentioning

confidence: 99%

“…Instead of mining all frequent itemsets and interesting association rules, our method only produces 2-itemsets to construct texture classification features and it can enhance temporal and spatial performance further. Because the approximation subband has only 1/4 amount of data as the original image, this reduce the time consuming greatly compared with [12]. Statistics of detail subbands are then employed as a part of texture features.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Combining frequent 2-itemsets and statistical features for texture classification in wavelet domain

Liu

Wang

et al. 2013

2013 International Conference on Advances in Computing, Communications and Informatics (ICACCI)

View full text Add to dashboard Cite

This paper studies a new method of texture image classification using the combination of frequent 2-itemsets and statistical features based on the discrete wavelet transform (DWT). DWT is firstly used to decompose images into different scale subbands. Then features differentiating textures for classification are extracted from these subbands. Frequently occurring local structures in images are captured from the approximation regions of one-level DWT decomposition images in the form of frequent 2-itemsets, which contain both structural and statistical information. To reduce redundancy, the paper adopts a diamond-shaped structure as the sliding window to construct transactions. Statistical features of the detail regions are then calculated and combined with frequent 2-itemsets to classify texture images. The experiments are conducted on two texture image sets, and the results show the good performance of this method.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Combining frequent 2-itemsets and statistical features for texture classification in wavelet domain

Liu

Wang

et al. 2013

2013 International Conference on Advances in Computing, Communications and Informatics (ICACCI)

View full text Add to dashboard Cite

show abstract

“…5) Texture features are mostly based on structural, statistical, or spectral properties. There are several methods for texture extraction using gray-level co-occurrence statistics [13], Gabor filters [17], windowed Fourier filters [2], association rules [34]. With the emergence of the Internet, content-based image retrieval (CBIR) has recently become one of the most important research topics spanning disciplines like image processing, computer vision, information retrieval, multidimensional access methods, databases, etc.…”

Section: B Luminance Featuresmentioning

confidence: 99%

Euler Vector for Search and Retrieval of Gray-Tone Images

Bishnu

Bhattacharya

Kundu³

et al. 2005

IEEE Trans. Syst., Man, Cybern. B

View full text Add to dashboard Cite

“…As such, directly addressing this issue, our fifth and final research question concerns the nature of theory co-occurrence in North American IS research studies. To address this question, we conducted an affinity (or "market-basket") analysis (Rushing, Ranganath, Hinke, & Graves, 2001) of our paper-level theory frequency data to identify the most common theory dyads and triads that North American IS research studies used between 1990 and 2013. Given the 318 unique theories under consideration, a standard combinatorial analysis indicated that there were a total of 50,403 possible theory dyads (i.e., cooccurring pairs of theories) and 5,309,116 possible theory triads (i.e., co-occurring groups of three theories) that the corpus's papers could have used.…”

Section: Research Question 4: the Evolving Theoretical Density Of Normentioning

confidence: 99%

Theory in North American Information Systems Research: A Culturomic Analysis

Soper¹,

Turel²

2016

CAIS

View full text Add to dashboard Cite

Abstract:Since its inception, North American information systems (IS) research has relied on a broad and varied collection of theories. The core of this theoretical landscape is an important determinant of the IS research community's identity, and, as such, researchers have discussed it extensively in recent years. Nevertheless, we know few concrete facts about the composition, consistency, or evolution of this theoretical core over time. Using a set of 318 theories in conjunction with n-gram analyses, we address these issues empirically by computationally analyzing the complete text of every research paper published in three leading North American IS journals over a 24-year period. In examining these 2,215 papers and more than 3.54 billion n-gram records, we identify the theories that constitute the overall core of North American IS research and provide insights into the evolution of that core. We further identify and quantify the nature of theoretical pluralism in North American IS research and examine the evolution of the theoretical density of IS research studies over time. Finally, our results shed light on the patterns of theory co-occurrence in North American IS research studies and demonstrate how such information can facilitate increasingly imperative efforts aimed at theory consolidation and generalization.

show abstract

Using association rules as texture features

Cited by 41 publications

References 19 publications

Combining frequent 2-itemsets and statistical features for texture classification in wavelet domain

Combining frequent 2-itemsets and statistical features for texture classification in wavelet domain

Euler Vector for Search and Retrieval of Gray-Tone Images

Theory in North American Information Systems Research: A Culturomic Analysis

Contact Info

Product

Resources

About