The spatial relation features for describing objects relationships within image

Saad, Mohd Zuwairi Mat; Muda, Zurina; Sahari, Noraidah; Hamid, Hamzaini Abdul; Hasan, Nur Hasanah binti Abu

doi:10.1109/iceei.2015.7352482

Cited by 2 publications

(3 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Basically, there are two types of image features commonly used as inputs in CBIR namely visual features and spatial features. Retrieving images using spatial relationship features refers to a method for determining the location of an object in an image as well as its relationship with other objects [21], [29]. Spatial relationship is a form of relationship that is uncertain or fuzzy and it depends on an individual to determine exactly the true form of relationship [15], [30].…”

Section: Spatial Relationship Image Featurementioning

confidence: 99%

See 1 more Smart Citation

Chest X-Ray Image Annotation based on Spatial Relationship Feature Extraction

Saad,

Mohsin,

Hamid

et al. 2023

AETiC

Self Cite

View full text Add to dashboard Cite

Digital imaging has become an essential element in every medical institution. Therefore, medical image retrieval such as chest X-ray (CXR) must be improved via novel feature extraction and annotation activities before they are stored into image databases. To date, many methods have been introduced to annotate medical images using spatial relationships after these features are extracted. However, the annotation performance for each method is inconsistent and does not show promising achievement to retrieve images. It is noticed that each method is still struggling with at least two big problems. Firstly, the recommended annotation model is weak because the method does not consider the object shape and rely on gross object shape estimation. Secondly, the suggested annotation model can only be functional for simple object placement. As a result, it is difficult to determine the spatial relationship feature after they are extracted to annotate images accurately. Hence, this study aims to propose a new model to annotate nodule location within lung zone for CXR image with extracted spatial relationship feature to improve image retrieval. In order to achieve the aim, a methodology that consists of six phases of CXR image annotation using the extracted spatial relationship features is introduced. This comprehensive methodology covers all cycles for image annotation tasks starting from image pre-processing until determination of spatial relationship features for the lung zone in the CXR. The outcome from applying the methodology also enables us to produce a new semi-automatic annotation system named CHEXRIARS which acts as a tool to annotate the extracted spatial relationship features in CXR images. The CHEXRIARS performance is tested using a retrieval test with two common tests namely the precision and recall (PNR). Apart from CHEXRIARS, three other annotation methods that are object slope, object projection and comparison of region boundaries are also included in the retrieval performance test. Overall, the CHEXRIARS interpolated PNR curve shows the best shape because it is the closest curve approaching the value of 1 on the X-axis and Y-axis. Meanwhile the value of area under curve for CHEXRIARS also revealed that this system attained the highest score at 0.856 as compared to the other three annotation methods. The outcome from the retrieval performance test indicated that the proposed annotation model has produced outstanding outcome and improved the image retrieval.

show abstract

Section: Spatial Relationship Image Featurementioning

confidence: 99%

“…The comparison of region boundaries was introduced to annotate the absolute and the relative object position in pairs with other objects [29]. Based on these two positions, the position of the main object and its relative position to the reference object can be known.…”

Section: Image Annotation Based On Comparison Of Region Boundariesmentioning

confidence: 99%

Chest X-Ray Image Annotation based on Spatial Relationship Feature Extraction

Saad,

Mohsin,

Hamid

et al. 2023

AETiC

Self Cite

View full text Add to dashboard Cite

show abstract

“…Similarly, visual search performed by aircraft technicians who check for airframe cracks and other indicators of metal fatigue before certifying an aircraft's airworthiness and ensuring the flight safety of aircrew and passengers may reduce to specific types of spatial reasoning. Scrutiny of airport luggage (Meuter & Lacherez, 2016) and satellite surveillance imagery by trained personnel for possible threats to national security or safety appears to also involve highly-developed spatial reasoning gained through years of training and work experience to support the primary task of visual search in their jobs (Guznov, Matthews, Warm, & Pfahler, 2017;! Saad, Muda, Ashaari, & Hamid, 2015).…”

mentioning

confidence: 99%

Four Ways of Reasoning About Space and Their Relation to Visual Search

Smith¹

View full text Add to dashboard Cite

A framework of spatial thought and language proposed by Chatterjee (2008) was extended to organize measures of spatial tasks (Uttal, Meadow, Tipton, Hand, Alden, Warren, & Newcombe, 2013). Uttal et al. posited that people reason about space based on recognizing and manipulating objects; dimensions of object features (intrinsic vs. extrinsic) and object movement (static vs. dynamic). Thus, Uttal et al. proposed four types spatial of spatial processes: Spatial visualization (intrinsic-static); spatial perception (extrinsic-static); mental rotation (intrinsic-dynamic); and spatial orientation (extrinsicdynamic). Each type of spatial process involves a particular focus of spatial thought, language, and task on the object proper (spatial visualization), its locative relations (spatial perception), manner of motion (mental rotation), or path of motion (spatial orientation). Undergraduates (N = 304) completed 14 spatial tasks identified by Uttal et al. (2013) as measures of the four spatial types. Participants also completed a visual search task that was hypothesized to involve spatial processes. Measurement models of the four-factor theory of spatial reasoning were tested. The four-factor model provided a good fit to the spatial ability measures and thus supported the proposed model. Although men performed better than women on most of the spatial measures, the model of spatial reasoning implied by the typology fit the data for both men and women. For visual search, a two-factor model of easy and difficult visual search fit the observed data. However, structural models relating all four spatial types to visual search did not converge, presumably because there were multiple unmeasured relations between visual search performance and the 14 spatial tasks. I would like to thank everyone who in some small way, sought to support the completion of this dissertation. I am who I am today because of you. I also acknowledge the gifted teaching and administrative staff at Carleton University. Thank-you for every effort you have made as professors and administrators. In particular, I would like to acknowledge the excellent administrative support I have received from Mme Etelle Bourassa. Etelle, your care and attention to detail has been greatly appreciated. To my family and friends, thank-you is just not enough. Without your support I am not sure I would have embarked on this journey, or been able to complete it. First to my wife, Deborah, to say that you were supportive and encouraging is an understatement. Your belief in me knew no end, through my fear of ever finishing, to your abiding patience and feedback in our many discussions about spatial reasoning, you were always there for me. Your encouragement is what kept me going and I look forward to everything the future has in store for us. To my children: Tom, Raeanna, Will, Ioan, Nick, Scott, and Alysha. Each of you have grown up in a learning environment to be the successful young women and men you are today. I hope that you will always be committed to lifelong learning-it will ...

show abstract

The spatial relation features for describing objects relationships within image

Cited by 2 publications

References 17 publications

Chest X-Ray Image Annotation based on Spatial Relationship Feature Extraction

Chest X-Ray Image Annotation based on Spatial Relationship Feature Extraction

Four Ways of Reasoning About Space and Their Relation to Visual Search

Contact Info

Product

Resources

About