New Method for Image Segmentation

Lalaoui, Lahouaoui; Mohamadi, Tayeb; Djaalab, Abdelhak

doi:10.1016/j.sbspro.2015.06.210

Cited by 27 publications

(10 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, only few studies were conducted by using quantitatives approach. The segmentation method with the algorithm mean shift may increase the accuracy value by 40.9% when compared with other methods such as region growing, and k-means [15], the mean shift algorithm also reduces work time by 40% when compared to the algorithm kmeans [16].…”

Section: Introductionmentioning

confidence: 99%

Examining the object-based and pixel-based image analyses for developing stand volume estimator model

Apriyanto

Jaya

Puspaningsih

2019

IJEECS

View full text Add to dashboard Cite

In the last two decades there has been significant leap on the spatial resolution of the satellite digital images which may be very useful for estimating stand parameter required for forest as well as environment management. This paper describes development of stand volume estimator models using SPOT 6 panchromatic and multispectral images with an object-based digital image analysis (OBIA) and conventional pixel-based approaches. The data used include panchromatic band with1.5m spatial resolution, and multispectral band with6m spatial resolution. The proposed OBIA technique with mean-shift algorithm was functioned to derive a canopy cover variable from the fusion of the panchromatic and multispectral, while the pixel-based vegetation index was used to develop model with an original pixel-size of 6 m. The estimator models were established based on 65 sample plots both measured in the field and images. The study found that the OBIA provides more accurate identification with Kappa Accuracy (KA) of 71% and Overall Accuracy (OA) of 86%. The study concluded that the best stand volume estimation model is the model that developed from the canopy cover (C) derived from OBIA i.e., v = 13.47e<sup>0.032C</sup> with mean deviation of only 0.92%, better than the model derived from conventional pixel-based approach, i.e., v = 0.0000067e<sup>16.48TNDVI</sup> with a mean deviation of 5.37%.

show abstract

Section: Introductionmentioning

confidence: 99%

Examining the object-based and pixel-based image analyses for developing stand volume estimator model

Apriyanto

Jaya

Puspaningsih

2019

IJEECS

View full text Add to dashboard Cite

show abstract

“…The fuzzy c‐means clustering (FCM) method is one of the cluster algorithms optimal enough in a classification process. The beauty of FCM clustering over K‐Means clustering is that the new clusters formation is possible through the monitoring of data points which have a closer membership degree to the existing classes (Lalaoui, Mohamadi, & Djaalab, ). On the other hand, Possibilistic c‐Means (PCM) clustering is too sensitive to the initialization of cluster and K‐Means clustering is sensitive to the selection of an initial cluster center values.…”

Section: Introductionmentioning

confidence: 99%

Clustered ANFIS weighing models for sweet lime (Citrus limetta) using computer vision system

Phate

Ramanathan

Palanisamy

2019

J Food Process Engineering

View full text Add to dashboard Cite

In the present research work, a clustered adaptive neuro‐fuzzy inference system (ANFIS) is used to develop the model of relationship between the weight with 1D and 2D features of the Indian sweet lime fruit extracted through the developed computer vision system. Initially, three clustering methods are used to classify the input data into a homogeneous group. Then, the self‐learning proficiency of an artificial neural network and the ability of fuzzy theory to deal with the uncertainty and nonlinearity are utilized by developing the ANFIS model. Finally, the clustered data is combined with the ANFIS models trained by two different learning methods are analyzed. The goodness‐of‐fit indicators close to unity and the lower values of the error performance metrics implies the adequacy, robustness, and superiority of the proposed method. Moreover, the lower value of Theil's coefficient for uncertainty (UII) signifies the credibility of the model to predict the weight of a sweet lime fruit. Practical applications The presented improved approach of clustered ANFIS modeling for weighing sweet lime fruit will be fruitful to the researchers, farmers, and engineers. In order to, design and develop the real time weight‐based grading, sorting, and packaging machine's knowledge about the fruit weight‐size relation is a basic requirement. Use of this proposed approach (computer vision linked with the clustered ANFIS model) will greatly reduce the handling of the fruit as well as the workload that are responsible for the qualitative and quantitative losses of fruits on bulk industrial scale. Also, this weighing model using 1D and 2D features will be more beneficial, faster, and economically viable substitute to the on‐field manual method used in agriculture specially during the sorting, grading, and packaging of sweet lime.

show abstract

“…Since the function relationships of each object-based window are regressed at a low resolution, we use the low-resolution LST as the input to the segmentation. In this paper, we apply the widely used SLIC algorithm, which generates superpixels by applying a k-means clustering approach classifying the input pixels into multiple classes based on their inherent distance from each other [33,36], to obtain the object-based window. The compactness (one important segmentation parameter) of all the segmentation procedures is set to a certain value, and the segmentation scales determine the counts of the objects.…”

Section: Object-based Window Strategymentioning

confidence: 99%

Object-Based Window Strategy in Thermal Sharpening

et al. 2019

View full text Add to dashboard Cite

The trade-off between spatial and temporal resolutions has led to the disaggregation of remotely sensed land surface temperatures (LSTs) for better applications. The window used for regression is one of the primary factors affecting the disaggregation accuracy. Global window strategies (GWSs) and local window strategies (LWSs) have been widely used and discussed, while object-based window strategies (OWSs) have rarely been considered. Therefore, this study presents an OWS based on a segmentation algorithm and provides a basis for selecting an optimal window size balancing both accuracy and efficiency. The OWS is tested with Landsat 8 data and simulated data via the “aggregation-then-disaggregation” strategy, and compared with the GWS and LWS. Results tested with the Landsat 8 data indicate that the proposed OWS can accurately and efficiently generate high-resolution LSTs. In comparison to the GWS, the OWS improves the mean accuracy by 0.19 K at different downscaling ratios, in particular by 0.30 K over urban areas; compared with the LWS, the OWS performs better in most cases but performs slightly worse due to the increasing downscaling ratio in some cases. Results tested with the simulated data indicate that the OWS is always superior to both GWS and LWS regardless of the downscaling ratios, and the OWS improves the mean accuracy by 0.44 K and 0.19 K in comparison to the GWS and LWS, respectively. These findings suggest the potential ability of the OWS to generate super-high-resolution LSTs over heterogeneous regions when the pixels within the object-based windows derived via segmentation algorithms are more homogenous.

show abstract

New Method for Image Segmentation

Cited by 27 publications

References 16 publications

Examining the object-based and pixel-based image analyses for developing stand volume estimator model

Examining the object-based and pixel-based image analyses for developing stand volume estimator model

Clustered ANFIS weighing models for sweet lime (Citrus limetta) using computer vision system

Object-Based Window Strategy in Thermal Sharpening

Contact Info

Product

Resources

About