Decision Map Research Articles

Multi-Focus Image Fusion in Transform Domain using Steerable Pyramids

In optical lenses of conventional cameras, depth of field is restricted to a particular range. Therefore, only those objects that are at a particular distance from the camera captured clearly with proper focus whereas objects at other distances in front of or behind the focus plane remain defocused and blurred. However, for accurately interpreting and analyzing images, it is desired to obtain images with every object in focus. Multi-focus image fusion is an effective technique to solve this problem by combining two or more images of the same scene taken with different focus settings into a single all-in-focus image with extended depth of field, which is very useful for human or machine perception. The main drawbacks of pixel based fusion methods are misalignment of decision map with boundary of focused objects and wrong decision in sub-regions of the focused or defocused regions which produce undesirable artifacts in the final fused image. Therefore frequency domain methods are more preferred then spatial domain methods. In previous years, many kinds of multi-scale transforms have been proposed and adopted for image fusion such as pyramid decomposition, discrete wavelet transform (DWT) , dual-tree complex wavelet transform (DTCWT) , and discrete cosine harmonic wavelet transform (DCHWT). These transforms are widely used as wavelets become dominant filters in most of the techniques but they still have drawbacks. Wavelets are the lack of translation invariance, especially in twodimensional (2D) signals and the poor selectivity in orientation. This can be overcome by steerable pyramid transform as one can choose the orientation before applying the filters. We have applied this method to achieve multi-focus image fusion of images which have different focus areas while capturing them. Experimental results shows that the proposed method affectively carried out fusion process as performance of the technique has been evaluated by various parameters namely mutual information, QABF factor used for edge perservance measuring and entropy etc.

Multifocus image fusion by combining with mixed-order structure tensors and multiscale neighborhood

In this study, we propose a new method for multifocus image fusion by combining with the structure tensors of mixed order differentials and the multiscale neighborhood. In this method, the structure tensor of an integral differential is utilized to detect the high frequency regions and the structure tensor of the fractional differential is used to detect the low frequency regions. To improve the performance of the fusion method, we propose a new focus measure based on the multiscale neighborhood technique to generate the initial fusion decision maps by exploiting the advantages of different scales. Next, based on the multiscale neighborhood technique, a post-processing method is used to update the initial fusion decision maps. During the fusion process, the pixels located in the focused inner regions are selected to produce the fused image. In order to avoid discontinuities in the transition zone between the focused and defocused regions, we propose a new “averaging” scheme based on the fusion decision maps at different scales. Our experimental results demonstrate that the proposed method outperformed the conventional multifocus image fusion methods in terms of both their subjective and objective quality.

Assessment of Land Degradation Status and Its Impact in Arid and Semi-Arid Areas by Correlating Spectral and Principal Component Analysis Neo-Bands

This paper aimed to assess the status of land degradation in arid and semi-arid areas based on a correlation analysis between spectral and statistical neo-bands. The methodology uses vegetation and soil spectral indices as the second Modified Soil Adjusted Vegetation Index (MSAVI2), Normalized Difference Bare Soil Index (NDBSI), Texture Index (NDTeI), Crust Index (CI), Top Soil Grain Size Index (GSI), Normalized Difference Sand Dune Index (NDSDI) and the first Specific Principal Component of the red, near infrared, shortwave infrared bands stacking (SPC1 R-NIR-SWIR1-SWIR2 ). The vegetation is considered here as the main object of soil sub-surface. Thus after all the spectral and the statistic neo-bands are performed on Landsat8 OLI sensor image, a linear regression is generated to assess their correlation with MSAVI2. Based on the visual interpretation and the regression curves the results show that the determination coefficient R 2 and the P values all significant as less than 0.0001. Each neo-band is weighted with its R 2 to improve its contribution to the model and the synthesis image obtained enhances the land degradation sensing in six classes; these are respectively named as ‘‘severe’’ (3139 km 2 ), ‘‘high’’ (6763 km 2 ), ‘‘moderate’’ (8341 km 2 ), ‘‘low’’ (7454 km 2 ), ‘‘very low’’ (6947 km 2 ) and ‘‘close to nil’’ (5437 km 2 ). This last image is summed with population layer to produce a decision map helpful for further government decision. At the end the degradation image has given interesting results for the detection of land degradation comparatively to derivation and comparison of individual indices.

Multi-Focus Image Fusion Through Gradient- Based Decision Map Construction and Mathematical Morphology

Multi-focus image fusion is an important technique that extracts sharp regions from multiple images and composites them into a fully focused image. In this paper, a novel spatial domain-based fusion algorithm for multi-focus images through gradient-based decision map construction and mathematical morphology is proposed. The contributions of this paper are: 1) a weighted kernel based on image gradient is proposed to measure focus regions; 2) the boundaries between focus and defocus regions are adjusted by morphological operations and free boundary condition-based active contour model. Though the weighted kernel, the focus regions are roughly identified. Moreover, after the morphological operations and the adjustment of boundaries using active contour model, the true boundaries between the focused and defocused regions are extracted. The experimental results demonstrate that the proposed algorithm performs better than the other eight representative fusion algorithms in both the qualitative and quantitative evaluations.

A fusion algorithm for infrared and visible images based on saliency analysis and non-subsampled Shearlet transform

This paper proposed a novel fusion method for the infrared and visible image based on the accurate extraction of the target region. Firstly, the super-pixels-based saliency analysis method is used to extract the salient regions of the infrared image and obtain the coarse contour of the infrared target. Then the multi-directional detection operators and the adaptive threshold algorithm are used to refine the boundary of the target region and obtain the fusion decision map. In order to capture the details of the visible image, non-subsampled Shearlet transform (NSST) is used to select the fusion coefficients of the background. Experimental results indicate that the proposed method is superior to other state of the-art methods in subjective visual and objective performance.

Abstract B33: Who am I? Improving quality of data collection for race/ethnicity and language

Abstract Introduction: Disparities in the quality of care provided to minorities has been documented in the literature. Reliable racial/ethnic reporting is critical, as initiatives to address healthcare disparities remain priorities on the national agenda. Hispanic children have been cited as having a higher incidence of leukemia/lymphoma but poorer survival rates. Accurate attribution of disease incidence and outcome to specific populations is central to ensuring appropriate access to care, family communication, resource distribution and funding for research. Analysis of 2000-2010 Hematology/Oncology data at Rady Children's Hospital San Diego (RCHSD) found a 13.02% discrepancy rate for race/ethnicity accuracy and 21% self-report rate. RCHSD is a pediatric medical center serving San Diego, Imperial, and southern Riverside counties in California, where Hispanic children comprise 42% of the population. While there is consensus regarding the importance of self-reporting of race/ethnicity, we identified both significant lack of self-reported race/ethnicity data and varied forms used to collect patient demographics at our site. Research has shown that most observers including administrative staff will accurately identify individuals as white or black, but Hispanic and multiracial individuals are often misidentified. Purpose: The Global Aim of this study was to improve resource allocation, patient-provider engagement and access to race/ethnicity and language data for research through correct race/ethnicity/language attribution. Our SMART aim was to implement a uniform and accurate system for data collection on race/ethnicity and language for the hematology/oncology population at our hospital with a reduction of missing and discrepant data to <2% within 6 months. Design/Methods: We conducted a quality improvement pilot project to achieve our Global Aim. Plan-Do -Study-Act method was used. P: Key stakeholders used Fishbone analysis and flow charting and several barriers to processes and possible interventions were identified. A new single form (English and Spanish) was created to obtain self-reported race/ethnicity and information on preferred language of written medical information, and preferred spoken language. A decision map to aid parents in question answering and information sheet were also created. Staff was trained to assist parents and document in the Electronic Medical Record (EMR). D: Self-reported data was obtained from 200 patients during a 6-week period. S: Pre and Post rates of self-reported race/ethnicity and language data completion and accuracy rates were compared. Accuracy rates for race/ethnicity and language were calculated by comparing existing demographic information in the EMR system at RCHSD versus demographic information collected with the new form. A: Data was presented to Hospital Quality Council; plan to embed tools in EMR and pilot a second population. Results: We found that race/ethnicity information was not collected in a uniform and consistent manner. Seven different demographic data collection forms were replaced by the new form. Discrepancy rate was reduced to 1.2%, a reduction of 90% (chi-square 19.073, p<0.001) and self-report rate was increased to 97%, an increase of 76% (chi-square 191.318, p<0.001). Forty-eight percent of individuals self-identified as Hispanic, 13% preferred Spanish as the language for spoken and written medical material, and in 21% patients, Spanish was the language spoken at home. Conclusion: Identifying barriers, reducing variability with a single data collection tool, and adjunct tools improved race/ethnicity/language accuracy. Next steps include definitive implementation and expansion to entire hospital. Collecting accurate information on patients' race/ethnicity and language should be a universal practice, enabling to understand and address disparities in childhood cancer. Citation Format: Paula Aristizabal, Foyinsola Ani, Erica Del Muro, Teresa Cassidy, William Roberts, Erin Stucky-Fisher, Maria Elena Martinez. Who am I? Improving quality of data collection for race/ethnicity and language. [abstract]. In: Proceedings of the Seventh AACR Conference on The Science of Health Disparities in Racial/Ethnic Minorities and the Medically Underserved; Nov 9-12, 2014; San Antonio, TX. Philadelphia (PA): AACR; Cancer Epidemiol Biomarkers Prev 2015;24(10 Suppl):Abstract nr B33.

Multi Sensor Image Fusion Using Saliency Map Detection

Image fusion is a process of generating an informative image from more than one complementary image. It finds applications in military, navigation, concealed weapon detection, medical imaging, digital photography and remote sensing etc. A new image fusion method based on two-scale image decomposition and saliency map detection is proposed in this paper for multi-sensor images. The algorithm is as follows: First, each source image is decomposed into base and detail layers. Second, saliency map of each source image is calculated with help of frequency tuned saliency map detection. Third, detail images are fused by using the proposed decision map based on the saliency maps and base layers are averaged to get the fused base layer. Finally, fused image is generated by taking the linear combination of fused base and detail layers. This algorithm is very advantageous because the saliency map used in this paper highlights the saliency information uniformly with well defined boundaries. So the decision map based on these saliency maps can effectively transfer the complementary information from source images to the fused image. Unlike traditional multi-scale decomposition fusion methods, proposed method uses two-scale decomposition to get base and detail layers. So it is computationally efficient. Outcomes of the proposed method are compared with existing multi-scale decomposition techniques along with spatial domain techniques with help of traditional and objective fusion metrics. Results reveal that proposed method outperforms the existing methods.

Novice Assistance Tool and Methodology: Design Decision and Task-Pattern Mapping

Novice Assistance Tool and Methodology: Design Decision and Task-Pattern Mapping

Novice Assistance Tool and Methodology: Design Decision and Task-Pattern Mapping

We present a possible method and tool to supportthe novice designers in the design tasks. Although in literaturestated that practitioners depend on memory and experiences,novice designers would take time to learn to acquire sufficient experience. The purpose of this research is to help novicedesigners to fulfill the usability goals that have determined by theexpert in designing a system. The proposed methodology and toolcan be considered as an assistance tool for novice designer indecision making in regards to prototype selection as well as thetask-pattern mapping template for pattern selection in fulfillingthe usability goal targeted. The tool was designed to manage thedecisions information and to recommend the chosen prototypebased on the Analytical Hierarchical Process (AHP) technique. Inoverall, about 87% of expert evaluators and prospective userswere agreed with the suggestion of prototype selection from theproposed tool. The findings from this study revealed that thecooperation from industry experts was valuable in determinedthe usability goal and direction and getting accumulativefeedbacks both from users and experts.

Robust object tracking based on weighted subspace reconstruction error with forward: backward tracking criterion

It is a challenging task to develop an effective and robust object tracking method due to factors such as severe occlusion, background clutters, abrupt motion, illumination variation, and so on. A tracking algorithm based on weighted subspace reconstruction error is proposed. The discriminative weights are defined based on minimizing reconstruction error with a positive dictionary while maximizing reconstruction error with a negative dictionary. Then a confidence map for candidates is computed through the subspace reconstruction error. Finally, the location of the target object is estimated by maximizing the decision map which combines the discriminative weights and subspace reconstruction error. Furthermore, the new evaluation method based on a forward–backward tracking criterion is used to verify the proposed method and demonstrates its robustness in the updating stage and its effectiveness in the reduction of accumulated errors. Experimental results on 12 challenging video sequences show that the proposed algorithm performs favorably against 12 state-of-the-art methods in terms of accuracy and robustness.

Random forest-based scheme using feature and decision levels information for multi-focus image fusion

Often captured images are not focussed everywhere. Many applications of pattern recognition and computer vision require all parts of the image to be well-focussed. The all-in-focus image obtained, through the improved image fusion scheme, is useful for downstream tasks of image processing such as image enhancement, image segmentation, and edge detection. Mostly, fusion techniques have used feature-level information extracted from spatial or transform domain. In contrast, we have proposed a random forest (RF)-based novel scheme that has incorporated feature and decision levels information. In the proposed scheme, useful features are extracted from both spatial and transform domains. These features are used to train randomly generated trees of RF algorithm. The predicted information of trees is aggregated to construct more accurate decision map for fusion. Our proposed scheme has yielded better-fused image than the fused image produced by principal component analysis and Wavelet transform-based previous approaches that use simple feature-level information. Moreover, our approach has generated better-fused images than Support Vector Machine and Probabilistic Neural Network-based individual Machine Learning approaches. The performance of proposed scheme is evaluated using various qualitative and quantitative measures. The proposed scheme has reported 98.83, 97.29, 98.97, 97.78, and 98.14 % accuracy for standard images of Elaine, Barbara, Boat, Lena, and Cameraman, respectively. Further, this scheme has yielded 97.94, 98.84, 97.55, and 98.09 % accuracy for the real blurred images of Calendar, Leaf, Tree, and Lab, respectively.

Image Fusion with Contrast Improving and Feature Preserving

The goal of image fusion is to obtain a fused image that contains most significant information in all input images which were captured by different sensors from the same scene. In particular, the fusion process should improve the contrast and keep the integrity of significant features from input images. In this paper, we propose a region-based image fusion method to fuse spatially registered visible and infrared images while improving the contrast and preserving the significant features of input images. At first, the proposed method decomposes input images into base layers and detail layers using a bilateral filter. Then the base layers of the input images are segmented into regions. Third, a region-based decision map is proposed to represent the importance of every region. The decision map is obtained by calculating the weights of regions according to the gray-level difference between each region and its neighboring regions in the base layers. At last, the detail layers and the base layers are separately fused by different fusion rules based on the same decision map to generate a final fused image. Experimental results qualitatively and quantitatively demonstrate that the proposed method can improve the contrast of fused images and preserve more features of input images than several previous image fusion methods.

A Novel Multi-Focus Image Fusion Method Based on Dual-Tree Shearlet Transform

In this paper, a multi-focus image fusion method based on Dual-Tree Compactly Supported Shearlet Transform (DT CSST) and Direction Decision Map (DDM) is proposed. DT CSST is a shift invariant modification of conventional Compactly Supported Shearlet Transform (CSST). Based on the mitigation of shift variance of CSST in DT CSST, a clearer fused image could be acquired through the General Image Fusion (GIF) method, and this image is called the initial fused image in this paper. The decision map is determined by the similarity of the initial fused image and the source images. The generation algorithm of the decision map in this paper takes advantage of the directional nature of DT CSST: every direction of the transform generates an initial directional decision map and then yields the final map through vote and smooth steps. This scheme is called DDM in this paper. The proposed method is evaluated by four groups of standard images. The results show that the proposed method is able to improve the quality indices compared with two algorithms which have excellent quality indices.

Integrated water management using feasible goals method and interactive decision maps: the case of Odivelas irrigation

In Mediterranean areas water scarcity is a real problem and stakeholders have conflicting visions and interests. This paper aims to determine feasible and efficient combinations of stakeholder goals using an integrated water management approach. A framework based on the Feasible Goals Method/Interactive Decision Maps (FGM/IDM) technique to approximate all Pareto optimal solutions of a linear multi-criteria model was developed. The model was applied to the Odivelas irrigated area in southern Portugal and a participative decision making was obtained considering multiple stakeholders goals that are in conflict.

A Decision Support System for Assessing Trade-Offs between Ecosystem Management Goals: An Application in Portugal

Cork oak (Quercus suber L.) and holm oak (Quercus rotundifolia) ecosystems are characteristic of Mediterranean forestry in Portugal. Even though cork is the most valuable product, these ecosystems provide multiple products and services. Assessing trade-offs between multiple goals is thus critical for the effectiveness of oak ecosystem management planning. This paper focuses on the development of a decision support system for oak ecosystems’ scenario analysis including multiple criteria. It includes an innovative decision support systems (DSS) functionality to assess trade-offs between the criteria that may support negotiation and consensus building between decision-makers and forest stakeholders. Specifically, a module that encapsulates the Feasible Goals Method/Interactive Decision Maps (FGM/IDM) technique is developed for interactive visualization of the Pareto frontier. The Pareto frontier illustrates the degree to which improving one particular criterion requires accepting sacrifices in the achievements of others. It thus provides information about trade-offs between competing decision-makers’ preferences. Results are discussed for a large-scale application encompassing over 1 million ha of cork and holm oak forest ecosystems in Southern Portugal. This study demonstrates the potential of the new DSS functionality to enhance multi-objective forest planning, namely by facilitating participation by stakeholders and providing transparency to the decision-making processes.

Who Am I? Improving Quality of Data Collection for Race/Ethnicity and Language in Pediatric Hematology/Oncology

Introduction: Disparities in the quality of care provided to minorities has been documented in the literature. Reliable racial/ethnic reporting is critical, as initiatives to address healthcare disparities remain priorities on the national agenda. Hispanic children have been cited as having a higher incidence of leukemia/lymphoma but poorer survival rates. Accurate attribution of disease incidence and outcome to specific populations is central to ensuring appropriate access to care, family communication, resource distribution and funding for research. Analysis of 2000-2010 Hematology/Oncology data at Rady Children’s Hospital San Diego (RCHSD) found a 13.02% discrepancy rate for race/ethnicity accuracy and 21% self-report rate. RCHSD is a pediatric medical center serving San Diego, Imperial, and southern Riverside counties in California, where Hispanic children comprise 42% of the population. While there is consensus regarding the importance of self-reporting of race/ethnicity, we identified both significant lack of self-reported race/ethnicity data and varied forms used to collect patient demographics at our site. Research has shown that most observers including administrative staff will accurately identify individuals as white or black, but Hispanic and multiracial individuals are often misidentified.Purpose: The Global Aim of this study was to improve resource allocation, patient-provider engagement and access to race/ethnicity and language data for research through correct race/ethnicity/language attribution. Our SMART aim was to implement a uniform and accurate system for data collection on race/ethnicity and language for the hematology/oncology population at our hospital with a reduction of missing and discrepant data to <2% within 6 months.Design/Methods: We conducted a quality improvement pilot project to achieve our Global Aim. Plan-Do -Study-Act method was used. P: Key stakeholders used Fishbone analysis and flow charting and several barriers to processes and possible interventions were identified. A new single form (English and Spanish) was created to obtain self-reported race/ethnicity and information on preferred language of written medical information, and preferred spoken language. A decision map to aid parents in question answering and information sheet were also created. Staff was trained to assist parents and document in the Electronic Medical Record (EMR). D: Self-reported data was obtained from 200 patients during a 6-week period. S: Pre and Post rates of self-reported race/ethnicity and language data completion and accuracy rates were compared. Accuracy rates for race/ethnicity and language were calculated by comparing existing demographic information in the EMR system at RCHSD versus demographic information collected with the new form. A: Data was presented to Hospital Quality Council; plan to embed tools in EMR and pilot a second population.Results: We found that race/ethnicity information was not collected in a uniform and consistent manner. Seven different demographic data collection forms were replaced by the new form. Discrepancy rate was reduced to 1.2%, a reduction of 90% (chi-square 19.073, p<0.001) and self-report rate was increased to 97%, an increase of 76% (chi-square 191.318, p<0.001). Forty-eight percent of individuals self-identified as Hispanic, 13% preferred Spanish as the language for spoken and written medical material, and in 21% patients, Spanish was the language spoken at home.Conclusions: Identifying barriers, reducing variability with a single data collection tool, and adjunct tools improved race/ethnicity/language accuracy. Next steps include definitive implementation and expansion to entire hospital. Collecting accurate information on patients’ race/ethnicity and language should be a universal practice, enabling to understand and address disparities in childhood cancer. DisclosuresNo relevant conflicts of interest to declare.

Dual-tree complex wavelet transform and image block residual-based multi-focus image fusion in visual sensor networks.

This paper presents a novel framework for the fusion of multi-focus images explicitly designed for visual sensor network (VSN) environments. Multi-scale based fusion methods can often obtain fused images with good visual effect. However, because of the defects of the fusion rules, it is almost impossible to completely avoid the loss of useful information in the thus obtained fused images. The proposed fusion scheme can be divided into two processes: initial fusion and final fusion. The initial fusion is based on a dual-tree complex wavelet transform (DTCWT). The Sum-Modified-Laplacian (SML)-based visual contrast and SML are employed to fuse the low- and high-frequency coefficients, respectively, and an initial composited image is obtained. In the final fusion process, the image block residuals technique and consistency verification are used to detect the focusing areas and then a decision map is obtained. The map is used to guide how to achieve the final fused image. The performance of the proposed method was extensively tested on a number of multi-focus images, including no-referenced images, referenced images, and images with different noise levels. The experimental results clearly indicate that the proposed method outperformed various state-of-the-art fusion methods, in terms of both subjective and objective evaluations, and is more suitable for VSNs.

Multi-focus image fusion using dictionary-based sparse representation

Multi-focus image fusion has emerged as a major topic in image processing to generate all-focus images with increased depth-of-field from multi-focus photographs. Different approaches have been used in spatial or transform domain for this purpose. But most of them are subject to one or more of image fusion quality degradations such as blocking artifacts, ringing effects, artificial edges, halo artifacts, contrast decrease, sharpness reduction, and misalignment of decision map with object boundaries. In this paper we present a novel multi-focus image fusion method in spatial domain that utilizes a dictionary which is learned from local patches of source images. Sparse representation of relative sharpness measure over this trained dictionary are pooled together to get the corresponding pooled features. Correlation of the pooled features with sparse representations of input images produces a pixel level score for decision map of fusion. Final regularized decision map is obtained using Markov Random Field (MRF) optimization. We also gathered a new color multi-focus image dataset which has more variety than traditional multi-focus image sets. Experimental results demonstrate that our proposed method outperforms existing state-of-the-art methods, in terms of visual and quantitative evaluations.

Multi-focus image fusion with dense SIFT

Multi-focus image fusion technique is an important approach to obtain a composite image with all objects in focus. The key point of multi-focus image fusion is to develop an effective activity level measurement to evaluate the clarity of source images. This paper proposes a novel image fusion method for multi-focus images with dense scale invariant feature transform (SIFT). The main novelty of this work is that it shows the great potential of image local features such as the dense SIFT used for image fusion. Particularly, the local feature descriptor can not only be employed as the activity level measurement, but also be used to match the mis-registered pixels between multiple source images to improve the quality of the fused image. In our algorithm, via the sliding window technique, the dense SIFT descriptor is first used to measure the activity level of source image patches to obtain an initial decision map, and then the decision map is refined with feature matching and local focus measure comparison. Experimental results demonstrate that the proposed method can be competitive with or even outperform the state-of-the-art fusion methods in terms of both subjective visual perception and objective evaluation metrics.

Multifocus image fusion method of Ripplet transform based on cycle spinning

The curvelet transform can represent images at both different scales and different directions. Ripplet transform, as a higher dimensional generalization of the curvelet transform, provides a new tight frame with sparse representation for images with discontinuities along C2 curves. However, the ripplet transform is lack of translation invariance, which causes the pseudo-Gibbs phenomenon on the edges of image. In this paper, the cycle spinning method is adopted to suppress the pseudo-Gibbs phenomena in the multifocus image fusion. On the other hand, a modified sum-modified-laplacian rule based on the threshold is proposed to make the decision map to select the ripplet coefficient. Several experiments are executed to compare the presented approach with other methods based on the curvelet, sharp frequency localized contourlet transform and shearlet transform. The experiments demonstrate that the presented fusion algorithm outperforms these image fusion works.