FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4376287987> ?p ?o ?g. }

• W4376287987 endingPage "109685" @default.
• W4376287987 startingPage "109685" @default.
• W4376287987 abstract "Shape analysis requires estimating object properties in many applications, including optical character recognition, tumor classification, skin cancer recognition, leaf and plant identification, and cell analysis. In particular, bit-quad-based linear expressions proposed by Gray and Duda for calculating the area and perimeter of binary images are widely used in the literature. Nevertheless, these formulas require computing 14 or 15 bit-quad patterns out of 16 possible, becoming critical in applications with limited computing resources. Hence, this paper introduces a method based on a single-layer artificial neural network (ANN) to discover new expressions to calculate the area and perimeter with fewer bit-quads than the original formulas without losing measuring accuracy. Besides, an iterative elimination process removes irrelevant bit-quads whose corresponding weights approach zero. After that, an inductive analysis from observing the learned weights provides interpretable formulas for the area and perimeter. Furthermore, the proposed approach is also applied to find bit-quad-based formulas for directly computing the contact perimeter property, whose original formula requires precomputing Gray’s area and perimeter of the object. In addition, aiming to show our method’s versatility in other applications, we address a real-world problem to discover a bit-quad-based formula to distinguish between two classes of loss of bone density caused by hyperthyroidism and aging in rats. The experimental results show that the proposed approach reduces by approximately half the bit-quads needed to calculate the area and perimeter of Gray and Duda. Likewise, the number of bit-quads to compute the contact perimeter is reduced from nine to six. Besides, the estimated value on test sets by all the found formulas is the same as their original counterparts. On the other hand, the classification of loss of bone density type using the found bit-quad-based formula reaches an accuracy of 100% in the test set. Therefore, the proposed method is an alternative to finding linear expressions with few bit-quads to measure basic object properties." @default.
• W4376287987 created "2023-05-13" @default.
• W4376287987 creator A5015247270 @default.
• W4376287987 creator A5057383073 @default.
• W4376287987 creator A5060157331 @default.
• W4376287987 creator A5091931961 @default.
• W4376287987 date "2023-10-01" @default.
• W4376287987 modified "2023-09-30" @default.
• W4376287987 title "Learning an Artificial Neural Network to Discover Bit-Quad-Based Formulas to Compute Basic Object Properties" @default.
• W4376287987 cites W1964064379 @default.
• W4376287987 cites W1980566883 @default.
• W4376287987 cites W1994940448 @default.
• W4376287987 cites W2032463446 @default.
• W4376287987 cites W2043131656 @default.
• W4376287987 cites W2108556791 @default.
• W4376287987 cites W2111933145 @default.
• W4376287987 cites W2143786310 @default.
• W4376287987 cites W2150464846 @default.
• W4376287987 cites W2151528296 @default.
• W4376287987 cites W2159498975 @default.
• W4376287987 cites W2895540242 @default.
• W4376287987 cites W3122437843 @default.
• W4376287987 cites W3146451788 @default.
• W4376287987 cites W3163373333 @default.
• W4376287987 cites W3194668998 @default.
• W4376287987 cites W3194730353 @default.
• W4376287987 doi "https://doi.org/10.1016/j.patcog.2023.109685" @default.
• W4376287987 hasPublicationYear "2023" @default.
• W4376287987 type Work @default.
• W4376287987 citedByCount "0" @default.
• W4376287987 crossrefType "journal-article" @default.
• W4376287987 hasAuthorship W4376287987A5015247270 @default.
• W4376287987 hasAuthorship W4376287987A5057383073 @default.
• W4376287987 hasAuthorship W4376287987A5060157331 @default.
• W4376287987 hasAuthorship W4376287987A5091931961 @default.
• W4376287987 hasConcept C111472728 @default.
• W4376287987 hasConcept C11413529 @default.
• W4376287987 hasConcept C138885662 @default.
• W4376287987 hasConcept C153180895 @default.
• W4376287987 hasConcept C154945302 @default.
• W4376287987 hasConcept C189950617 @default.
• W4376287987 hasConcept C2524010 @default.
• W4376287987 hasConcept C2781238097 @default.
• W4376287987 hasConcept C33923547 @default.
• W4376287987 hasConcept C41008148 @default.
• W4376287987 hasConcept C48372109 @default.
• W4376287987 hasConcept C50644808 @default.
• W4376287987 hasConcept C94375191 @default.
• W4376287987 hasConcept C98503990 @default.
• W4376287987 hasConceptScore W4376287987C111472728 @default.
• W4376287987 hasConceptScore W4376287987C11413529 @default.
• W4376287987 hasConceptScore W4376287987C138885662 @default.
• W4376287987 hasConceptScore W4376287987C153180895 @default.
• W4376287987 hasConceptScore W4376287987C154945302 @default.
• W4376287987 hasConceptScore W4376287987C189950617 @default.
• W4376287987 hasConceptScore W4376287987C2524010 @default.
• W4376287987 hasConceptScore W4376287987C2781238097 @default.
• W4376287987 hasConceptScore W4376287987C33923547 @default.
• W4376287987 hasConceptScore W4376287987C41008148 @default.
• W4376287987 hasConceptScore W4376287987C48372109 @default.
• W4376287987 hasConceptScore W4376287987C50644808 @default.
• W4376287987 hasConceptScore W4376287987C94375191 @default.
• W4376287987 hasConceptScore W4376287987C98503990 @default.
• W4376287987 hasLocation W43762879871 @default.
• W4376287987 hasOpenAccess W4376287987 @default.
• W4376287987 hasPrimaryLocation W43762879871 @default.
• W4376287987 hasRelatedWork W1558456818 @default.
• W4376287987 hasRelatedWork W2020478166 @default.
• W4376287987 hasRelatedWork W2033914206 @default.
• W4376287987 hasRelatedWork W2046077695 @default.
• W4376287987 hasRelatedWork W2058182359 @default.
• W4376287987 hasRelatedWork W2146076056 @default.
• W4376287987 hasRelatedWork W2163831990 @default.
• W4376287987 hasRelatedWork W2386387936 @default.
• W4376287987 hasRelatedWork W2536452361 @default.
• W4376287987 hasRelatedWork W3003836766 @default.
• W4376287987 hasVolume "142" @default.
• W4376287987 isParatext "false" @default.
• W4376287987 isRetracted "false" @default.
• W4376287987 workType "article" @default.