&lt;title&gt;Objective evaluation of four SAR image segmentation algorithms&lt;/title&gt;

Gregga, Jason B.; Gustafson, Steven C.; Power, Gregory J.

doi:10.1117/12.438228

Cited by 5 publications

(6 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[1][2][3] The segmentations are two-dimensional images consisting of segmented objects that are stored as closed polygons. The closed polygons are compared onedimensionally by imagining each two-dimensional object shape edge as consisting of a sequence of connected points on a complex plane thus transforming each x and y coordinate into a one-dimensional complex number x + iy.…”

Section: Introductionmentioning

confidence: 99%

<title>Correlators for rank order shape similarity measurement</title>

Gregga

Power

Iftekharuddin

2002

Optical Pattern Recognition XIII

Self Cite

View full text Add to dashboard Cite

Correlators have been used for detecting shapes but not as often for measuring shape similarity. The complex inner product (CIP) has been used in various formulations as a shape similarity measure. The CIP is essentially a one-dimensional correlation approach to measuring similarity. One-dimensional variants of the correlation techniques including the matched filter (MF), phase-only filter (POF), and amplitude-modulated phase only filter (AMPOF) are shown to measure shape similarity in a trend that approaches human perception, however, clear performance differences are noted. The results show that the best correlator for measuring shape similarity is not the best correlator for detecting a shape. It is suggested that detection and shape similarity are fundamentally different functions that are in opposition to some degree. Ideal detection and ideal similarity measurement functions are explored. The degree to which various formulations of correlators approach the ideal functions of detection and similarity measurement are shown as well as results from human psychophysical experiments.

show abstract

Section: Introductionmentioning

confidence: 99%

<title>Correlators for rank order shape similarity measurement</title>

Gregga

Power

Iftekharuddin

2002

Optical Pattern Recognition XIII

Self Cite

View full text Add to dashboard Cite

show abstract

“…[1][2][3][4][5][6] This research is expanded here to examine three-dimensional data. The evaluation of three-dimensional objects can be thought of as evaluating the shape, size, and surface.…”

Section: Introductionmentioning

confidence: 99%

<title>Toward a comparative analysis of three-dimensional shape measures</title>

Power

Gregga

2002

SPIE Proceedings

Self Cite

View full text Add to dashboard Cite

Measuring a system's capability to acquire accurate three-dimensional shape is important for validating the system for a particular application. Various system factors are reviewed that contribute to inaccurate shape. The system factors are classified into various classes based on types of measurement errors produced. As shown in this paper, different shape measures do not do a complete evaluation but provide different information depending on the type of error. A partial-directed hausdorf (PDH) and complex inner product (CIP) measure that were previously introduced to measure two-dimensional shapes are now extended to measure three-dimensional shapes. PDH measures how close the 3-D surface is to the ideal 3-D surface within a predefined acceptable error margin while the CIP measures how well the 3-D surface correlates to the ideal 3-D surface. Two variants of the CIP measure are used in this paper including a pure phase only filter and a normalized matched filter. The CIP measure is compared to the Procrustes metric for comparing shapes. Using a test case shape, the measures are compared and shown to provide varying information. Alone, any one measure cannot provide complete shape information. Combining measures provides a more robust three-dimensional shape measurement system. The shape measures are demonstrated first on three-dimensional data with controlled variation and then on laser ranging data.

show abstract

“…Some preliminary experiments were conducted to show that using image segmentation quality metric alone does not necessarily consistent with the quality of ATR performance. 3 …”

Section: Introductionmentioning

confidence: 99%

“…where cip ranges from zero to one as one for the perfect match [3]. All the above mentioned measures can be used together to achieve a composite measure.…”

mentioning

confidence: 99%

“…All the above mentioned measures can be used together to achieve a composite measure. However, there are no clear ways to determine what kind of composite measure should be used under what situation [3]. In intra-algorithmic comparison, the measures are used to compare the segmentation result with the truth data that is often a master segmentation created by a human analyst.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Evaluation of synthetic aperture radar image segmentation algorithms in the context of automatic target recognition

2002

Self Cite

View full text Add to dashboard Cite

The public reporting burden for this collection of information is estimated to average 1 hour per response, including the time for reviewing instructions, searching existing data sources, searching existing data sources, gathering and maintaining the data needed, and completing and reviewing the collection of information. Send comments regarding this burden estimate or any other aspect of this collection of information, including suggestions for reducing this burden, to Department of Defense, Washington Headquarters Services, Directorate for Information DISTRIBUTION/AVAILABILITY STATEMENTApproved for public release; distribution is unlimited. SUPPLEMENTARY NOTES© 2002 SPIE. This work is copyrighted. The United States has for itself and others acting on its behalf an unlimited, paid-up, nonexclusive, irrevocable worldwide license. Any other form of use is subject to copyright restrictions.Paper was presented at the Optical Science and Technology (SPIE) Conference, Seattle, WA, 7 July 2002. ABSTRACTImage segmentation is a process to extract and organize information energy in the image pixel space according to a prescribed feature set. It is often a key preprocess in automatic target recognition (ATR) algorithms. In many cases, the performance of image segmentation algorithms will have significant impact on the performance of ATR algorithms. Due to the variations in feature set definitions and the innovations in the segmentation processes, there is large number of image segmentation algorithms existing in the ATR world. The problem is which image segmentation algorithm performs best for an ATR application. There are a number of measures to evaluate the performance of segmentation algorithms, such as Percentage Pixels Same (pps), Partial Directed Hausdorff (pdh) , and Complex Inner Product (cip). In the research, we found that the combination of the three measures shows effectiveness in the evaluation of segmentation algorithms against truth data (human master segmentation). However, we don't know what are the impact of those measures in the performance of ATR algorithms that are commonly measured by Probability of detection (P Det ), Probability of false alarm (P FA ), Probability of identification (P ID ), etc. In all practical situations, ATR boxes are implemented without human observer in the loop. The performance of synthetic aperture radar (SAR) image segmentation should be evaluated in the context of ATR rather than human observers. SUBJECT TERMS Executive SummaryImage segmentation is a process to extract and organize information energy in the image pixel space according to a prescribed feature set. It is often a key preprocess in automatic target recognition (ATR) algorithms. In many cases, the performance of image segmentation algorithms will have significant impact on the performance of ATR algorithms. Due to the variations in feature set definitions and the innovations in the segmentation processes, there is large number of image segmentation algorithms existing in the ATR world. The problem is which i...

show abstract

<title>Objective evaluation of four SAR image segmentation algorithms</title>

Cited by 5 publications

References 10 publications

<title>Correlators for rank order shape similarity measurement</title>

<title>Correlators for rank order shape similarity measurement</title>

<title>Toward a comparative analysis of three-dimensional shape measures</title>

Evaluation of synthetic aperture radar image segmentation algorithms in the context of automatic target recognition

Contact Info

Product

Resources

About