Adaptive Directional Filter Research Articles

Adaptively Directed Image Restoration Using Resilient Backpropagation Neural Network

In this modern era, visual data transmission, processing, and analysis play a vital role in daily life. Image denoising is the process of approximately estimating the original version of a degraded image. The presence of unexpected noise (e.g., fixed, random, and Gaussian) is the root cause of degradation, which has been reduced to some extent by many linear and non-linear filters based on a median value. The real issue is developing a strategy that should be generalized enough to effectively restore an image corrupted with multi-nature noise. Many researchers have developed novel concepts, but their tactics must acquire the highest performance in this area. This article proposes a constrained strategy for this problem, i.e., an adaptively directed denoising filter (ADD filter) based on a neural network. It consists of three major stages: training, filtering, and enhancing. First, we train a feed-forward back-propagation neural network on noisy and noise-free pixels for effective differentiation. Second, we apply a one-pass selective filter to the noisy image. The objective of this one-pass filter is to minimize noise using an adaptive median or directional filter based on density. Finally, the iterative directional filter is applied to the pre-processed image to enhance its visual quality. The extensive experiments depict that the proposed system has achieved better subjective results and improved local (structural similarity) and global (peak signal-to-noise ratio or mean square error) statistical measures.

Design of complex adaptive multiresolution directional filter bank and application to pansharpening

This paper proposes a new 2-D transform design, namely complex adaptive multiresolution directional filter bank, to represent the spatial orientation features of an input image adaptively. The proposed design is completely shift invariant and represents the input image by one low-pass and multiscale N directional band-pass subbands. Here, N represents estimated number of dominant directions present in the input image. Our design consists of two main filter bank stages. A fix partitioned complex-valued directional filter bank (CDFB) is at the core of the design followed by a novel partition filter bank stage. Fine partitioning of the CDFB subbands is used to get the adaptive nature of the proposed transform. The partitioning decision is made based on the directional significance of range of CDFB subband angle selectivity in the input image. Partition filter bank stage which nonuniformly partitions the CDFB subbands provides total N dominant direction selective subbands. Local orientation map of the input image is used to determine the dominant directions and hence N. For better sparsity properties, we design the multiresolution stage with filters having high vanishing moments and better frequency selectivity. Applicability of the proposed adaptive design is shown for pansharpening of multispectral images. Our proposed pansharpening approach is evaluated on images captured using QuickBird and IKONOS-2 satellites. Results obtained using the proposed approach on these datasets show considerable improvements in qualitative as well as quantitative evaluations when compared to state-of-the-art pansharpening approaches including transform-based methods.

Low bit-rate compression of underwater imagery based on adaptive hybrid wavelets and directional filter banks

A new underwater video compression technique based on adaptive hybrid wavelets and directional filter banks is proposed to achieve both high coding efficiency and good reconstruction quality at very low-bit rates. A key application is the real-time transmission of video through acoustic channels with limited bandwidth, from an autonomous underwater vehicle to a surface station, e.g., for man-in-the-loop monitoring and inspection operations. For intra-frame coding, the method maintains details in texture regions at relatively low bit rates, and overcomes the ringing artifacts within smooth regions. For inter-frame coding, improved efficiency is achieved by making use of: (1) a new spatio-temporal just-noticeable-distortion model to remove perceptual redundancy; (2) motion interpolation to reduce bit rate; and (3) variable-precision in quantizing the residual error. Experiments with underwater video sequences are presented to assess the effectiveness of the proposed approach, in comparison to traditional wavelet-based techniques.

GEOLGICAL STRUCTURE MAPPING OF THE BENTONG-RAUB SUTURE ZONE, PENINSULAR MALAYSIA USING PALSAR REMOTE SENSING DATA

Abstract. The Bentong-Raub Suture Zone (BRSZ) of peninsular Malaysia was selected as case study to evaluate the capability of the Phased Array type L-band Synthetic Aperture Radar (PALSAR) satellite remote sensing data for structural geology mapping in tropical environments. The structural elements in the BRSZ were enhanced using multi-polarization configuration of PALSAR data at a regional scale. Adaptive local sigma and directional filters were applied to PALSAR data for detailed structural mapping. Numerous tectonic lineaments with consistent variation in trend, length and density were detected in the study area. Structural analysis of the BRSZ reveals that two distinct parts can be defined, a western part affected mainly by ductile fabrics in the Cameron Highlands and an eastern part affected mainly by brittle deformation in the BRSZ. Ductile deformation indicates several generation of folding in the Cameron Highlands. Several faults, joints and fractures represent brittle deformation events in the BRSZ. The results of this study demonstrate the usefulness of PALSAR satellite remote sensing data for mapping geological structures in tropical environments.

INTEGRATION OF PALSAR AND ASTER SATELLITE DATA FOR GEOLOGICAL MAPPING IN TROPICS

Abstract. This research investigates the integration of the Phased Array type L-band Synthetic Aperture Radar (PALSAR) and the Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) satellite data for geological mapping applications in tropical environments. The eastern part of the central belt of peninsular Malaysia has been investigated to identify structural features and mineral mapping using PALSAR and ASTER data. Adaptive local sigma and directional filters were applied to PALSAR data for detecting geological structure elements in the study area. The vegetation, mineralogic and lithologic indices for ASTER bands were tested in tropical climate. Lineaments (fault and fractures) and curvilinear (anticline or syncline) were detected using PALSAR fused image of directional filters (N-S, NE-SW, and NW-SE).Vegetation index image map show vegetation cover by fusing ASTER VNIR bands. High concentration of clay minerals zone was detected using fused image map derived from ASTER SWIR bands. Fusion of ASTER TIR bands produced image map of the lithological units. Results indicate that data integration and data fusion from PALSAR and ASTER sources enhanced information extraction for geological mapping in tropical environments.

An enhanced depth map based rendering method with directional depth filter and image inpainting

Depth image-based rendering (DIBR), which is used to render virtual views with a color image and the corresponding depth map, is one of the key techniques in the 2D to 3D video conversion process. In this paper, a novel method is proposed to partially solve two puzzles of DIBR, i.e. visual image generation and hole filling. The method combines two different approaches for synthesizing new views from an existing view and a corresponding depth map. Disoccluded parts of the synthesized image are first classified as either smooth or highly structured. At structured regions, inpainting is used to preserve the background structure. In other regions, an improved directional depth smoothing is used to avoid disocclusion. Thus, more details and straight line structures in the generated virtual image are preserved. The key contributions include an enhanced adaptive directional filter and a directional hole inpainting algorithm. Experiments show that the disocclusion is removed and the geometric distortion is reduced efficiently. The proposed method can generate more visually satisfactory results.

Integrating PALSAR and ASTER data for mineral deposits exploration in tropical environments: a case study from Central Belt, Peninsular Malaysia

Remote sensing investigation for mineral deposits exploration in tropical environments is not completely implemented due to obstacles imposed by tropical climate. Recent challenge is to use the most suitable recent generation of remote sensing data and image processing approaches for the detection of lithological units and structural features associated with epithermal and polymetallic vein-type mineralisation, which are concealed by tropical rainforest. This research investigates the integration of the Phased Array type L-band Synthetic Aperture Radar (PALSAR) and the Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) satellite data for geological mapping applications in tropical environments. The eastern part of the Central Belt of Peninsular Malaysia with high potential for gold prospecting has been investigated as a case study to identify structural features and mineral assemblages using PALSAR and ASTER data. Adaptive local sigma and directional filters were applied to PALSAR data for detecting geological structure elements in the study area. Vegetation, mineralogic and lithologic indices for ASTER bands were tested in tropical climate. Lineaments (fault and fractures) and curvilinear (anticline or syncline) were detected using PALSAR image map of directional filters (N–S, NE–SW and NW–SE).Vegetation index image map show vegetation cover using ASTER visible and near-infrared radiation (VNIR) bands. High concentration of clay minerals zone was detected using image map derived from ASTER shortwave infrared (SWIR) bands. ASTER thermal infrared (TIR) bands produced image map of the lithological units. Results indicate that data integration from PALSAR and ASTER sources enhanced information extraction for geological mapping in tropical environments. The study presented here encourages further applications of satellite remote sensing data integration for mapping structural elements, hydrothermal alteration minerals and lithological units associated with epithermal and polymetallic vein-type mineralisation in tropical environments.

Directional joint bilateral filter for depth images.

Depth maps taken by the low cost Kinect sensor are often noisy and incomplete. Thus, post-processing for obtaining reliable depth maps is necessary for advanced image and video applications such as object recognition and multi-view rendering. In this paper, we propose adaptive directional filters that fill the holes and suppress the noise in depth maps. Specifically, novel filters whose window shapes are adaptively adjusted based on the edge direction of the color image are presented. Experimental results show that our method yields higher quality filtered depth maps than other existing methods, especially at the edge boundaries.

Structural mapping using PALSAR data in the Central Gold Belt, Peninsular Malaysia

The Central Gold Belt (CGB) of Peninsular Malaysia has been investigated to map structural elements associated with gold mineralization using the Phased Array type L-band Synthetic Aperture Radar (PALSAR) satellite remote sensing data. Gold mineralization in this belt is structurally controlled and associated with steeply dipping faults and fold hinges. Adaptive local sigma and directional filters were applied to PALSAR data for tracing structural elements associated with gold mineralization. Structural features along the Bentong–Raub Suture Zone have been identified as highly potential areas for gold prospecting. Four sets of lineaments trending N–S, NE–SW, NNW–SSE and ESE–WNW were identified. Results of this study demonstrate the applicability of PALSAR remote sensing data to assist gold exploration in the CGB particularly in reducing costs related to exploration for epithermal and polymetallic vein-type mineralization in tropical environments.

Local adaptive directional color filter array interpolation based on inter-channel correlation

In this paper, we present a novel color image demosaicking algorithm. The algorithm consists of two steps: an interpolation step and a refinement step. The missing green color information is first interpolated by using the color channel difference. In the refinement step, a local weighted directional interpolation method guided by the pre-interpolated green channel is applied to refine the interpolation results along the determined interpolation direction. Lastly, post-processing is implemented to output the final demosaicked full color image. Due to well estimating the interpolation directions based on reliable inter-channel correlation, the interpolation accuracy is guaranteed, besides, an effective post-processing was implemented to reduce the interpolation artifacts. As a result, compared with the latest demosaicking algorithms, experiments showed that the proposed method provides superior performance in terms of both objective and subjective image qualities.

The easy block Hadamard transform: A new adaptive directional Hadamard transform for sparse image representation

In order to get an efficient image representation, we introduce a new locally adaptive Hadamard transform, called Easy Block Hadamard Transform (EBHT). EBHT is a type of directional Hadamard transform, which can be adapted to the image geometry in each block. Firstly, the image is divided into eight equal-sized squares and the adaptive directional Hadamard filter is employed to get the low-pass data and high-pass data. In the further level of the filter bank algorithm, we just divide the low-pass image into four equal-sized squares. EBHT is very simple, but effective. Numerical results show the excellent efficiency of the EBHT for sparse image representation.

Speckle Reduction in Ultrasound Images Using Nonisotropic Adaptive Filtering

In this article, a speckle reduction approach for ultrasound imaging that preserves important features such as edges, corners and point targets is presented. Speckle reduction is an important problem in coherent imaging, such as ultrasound imaging or synthetic aperture radar, and many speckle reduction algorithms have been developed. Speckle is a non-additive and non-white process and the reduction of speckle without blurring sharp features is known to be difficult. The new speckle reduction algorithm presented in this article utilizes a nonhomogeneous filter that adapts to the proximity and direction of the nearest important features. To remove speckle without blurring important features, the location and direction of edges in the image are estimated. Then for each pixel in the image, the distance and angle to the nearest edge are efficiently computed by a two-pass algorithm and stored in distance and angle maps. Finally for each pixel, an adaptive directional filter aligned to the nearest edge is applied. The shape and orientation of the adaptive filter are determined from the distance and angle maps. The new speckle reduction algorithm is tested with both synthesized and real ultrasound images. The performance of the new algorithm is also compared with those of other speckle reduction approaches and it is shown that the new algorithm performs favorably in reducing speckle without blurring important features.

Color image processing using adaptive vector directional filters

A new class of filters for multichannel image processing is introduced and analyzed. This class constitutes a generalization of vector directional filters. The proposed filters use fuzzy transformations of the angles among the different vectors to adapt to local data in the image. The principle behind the new filters is explained and comparisons with other popular nonlinear filters are provided. The specific case of color image processing is studied as an important example of multichannel image processing. Simulation results indicate that the new filters offer some flexbility and have excellent performance.

Color image filters: the vector directional approach

Processing of color image data using directional information has received increased attention lately due to the introduction of the vector directional filters. These rank-ordered type filters utilize the direc- tion of color vectors to enhance, restore and segment color images. First, the different vector directional filters already in use are presented, focusing on their similarities and differences and, second, new adaptive vector directional filters are introduced. Fuzzy as well as nearest neigh- bor structures are utilized to determine the weights in the proposed adaptive filters. Simulation studies involving color images are used to assess the performance of the different vector directional filters and to compare them with other commonly used nonlinear filters. The simula- tion studies reported indicate that the new adaptive filters are computa- tionally attractive and have excellent performance. © 1997 Society of Photo- Optical Instrumentation Engineers. (S0091-3286(97)02609-3)

Tracking of coherent broadband sources using adaptive directional filter with maximally flat responses at null directions

A new algorithm for tracking coherent broadband sources in linear arrays employing tapped delay line processing is presented and investigated. To resolve M-directional broadband sources with a maximum coherent group size of M a , the original ( M + l)-element power inversion array is augmented by M a − 1 elements to result in a total of M a identical but spatially shifted ( M + l)-element subarrays. Using this technique, each broadband source is individually tracked in a cyclical time multiplexed manner, by steering a broadband null in each subarray formed from the use of a tapped delay line filter with weights constrained to have maximally flat frequency response at the nulling direction, to minimise the spatially averaged power output. Since the new algorithm updates only one tapped delay line filter at any instant, the overall implementation complexity of the proposed algorithm is comparable to that of using the LMS algorithm directly on a broadband array. However, unlike the latter algorithm, the new algorithm possesses a convergence behaviour that is significantly faster and almost independent of the external noise environment and provides the sources' directions directly without employing a root-finding routine.

Broadband source tracking using adaptive directional filter with maximally flat responses at null directions

A new algorithm for the tracking of broadband sources in linear arrays employing tapped delay line processing is presented and investigated. Using this technique, each broadband source is individually tracked in a time-multiplexed manner by steering a broadband null formed from the use of a tapped delay line filter whose weights are constrained to have a maximally flat frequency response at the nulling direction. To ensure that the other nulls are not changed while a particular null is being adjusted, a beamformer is employed to preprocess the element signals before adaptive processing. Since the new algorithm updates only one tapped delay line filter at any instant, the overall implementation complexity of the proposed algorithm is comparable with using the LMS algorithm directly on a broadband array. However, unlike the latter algorithm, the convergence behavior of the new algorithm is significantly faster and is almost independent of the external noise environment.

Image sequence enhancement based on adaptive symmetric order statistics

Statistical properties of the spatiotemporal center-weighted median (CWM) filter for image sequences are investigated. It is statistically shown that the CWM filter preserves image structures under motion at the expense of noise suppression. To improve the CWM filter so it can be effectively used in image sequence processing, the adaptive directional CWM filter (ADCWM) is proposed. This filter utilizes a multistage filtering structure, based on adaptive symmetric order statistic (ASOS) operators which produce a pair of order statistics symmetric about the median. The ASOSs are selected by using adaptive parameters adjusted by local image statistics. It is shown experimentally that the proposed filter can preserve image structures while attenuating noise without the use of motion estimation.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

Adaptive Interference Cancellation in Nyquist Rate Scanned Arrays

A concept for adaptive directional filtering in a Nyquist rate scanned array based on time-domain sampling in the array sum channel is presented. By this method the adaptation rate may be independent of the scan rate in contrast to arrays with adaptive weight setting in the array element channels.