MétaCan
Menu
Back to cohort
Record W2104853399 · doi:10.1109/igarss.1989.575840

Textural Filtering For SAR Image Processing

2005· article· en· W2104853399 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldEngineering
TopicRemote-Sensing Image Classification
Canadian institutionsUniversité de Sherbrooke
Fundersnot available
KeywordsArtificial intelligencePixelImage textureComputer visionComputer scienceTexture (cosmology)Pattern recognition (psychology)Feature (linguistics)Image processingMultispectral imageImage (mathematics)

Abstract

fetched live from OpenAlex

Texture is an important feature which can be used in the interpretation of remotely sensed imagery. This paper presents exam- ples of the application of a new approach to the textural filtering and enhancing of digital images. Satisfactory results are obtained in pro- cessing images from both natural textures and airborne SAR scenes. Textural filtering of SAR images can be useful in improving the dis- crimination between lithologic units with different surface-roughness characteristics. One application example is discussed in which textural features show different discrimination performances before and after textural filtering. I. INTRODUCTION A digital image is usually characterized by two main aspects: Tone and texture. The image tone consists of background grey- level variations of the pixels throughout the entire image. The im- age texture represents the intrinsic spatial variability of neighbor- ing pixel values for each pixel within the image. It follows that methods of image analysis can be broadly divided into two cate- gories: The spectral one and the textural one. In spectral analysis the interest is in studying broad variations of the grey levels of the pixels (image tone) in mono-, or multispectral bands. The aim of textural analysis is to characterize spatially the grey-level relation- ships between the pixels of a neighborhood. Tone and texture are usually not independent in an image, so that when processing it we observe that one influences the other. The image tone characteris- tics can be separated from the texture, and these two features can be processed independently. This situation promises to be very use- ful in enhancing the texture perception on the one hand, and in improving the result of conventional texture analysis on the other. Digital filtering techniques are widely used in image processing and interpretation ( 11-(3). Based on the traditional concept of Fourier analysis, the three basic classical filters are the low-pass, the high-pass, and the band-pass. They are widely used in remote sensing for noise suppression, edge detection, smoothing, and en- hancement. However, these filters are unable to separate the tone and texture because in an image the two features affect each other. A new method of texture analysis has been recently proposed by He and Wang (4), (5), where a texture image can be described by the characteristics of its texture spectrum. The purpose of this pa- per is to design a textural filter in the texture spectrum domain to remove the regional intensity background variation, termed the tex- tural noise. The performance of the new textural filter on several of Brodatz's natural images (8) is discussed. In airborne SAR terms, the new filter has been shown to enhance the textural perception and improve the discrimination between different rock units.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.819
Threshold uncertainty score0.360

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.017
GPT teacher head0.248
Teacher spread0.231 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Quick stats

Citations7
Published2005
Admission routes1
Has abstractyes

Explore more

Same topicRemote-Sensing Image ClassificationFrench-language works237,207