http://dr.lib.sjp.ac.lk/handle/123456789/164 Wed, 07 Jan 2026 06:06:34 GMT 2026-01-07T06:06:34Z http://dr.lib.sjp.ac.lk/handle/123456789/9025 Deep learned compact binary descriptor with a lightweight network-in-network architecture for visual description Bandara, R; Ranathunga, L; Abdullah, N.A Binary descriptors have been widely used for real-time image retrieval and correspondence matching. However, most of the learned descriptors are obtained using a large deep neural network (DNN) with several million parameters, and the learned binary codes are generally not invariant to many geometrical variances which is crucial for accurate correspondence matching. To address this problem, we proposed a new learning approach using a lightweight DNN architecture via a slack of multiple multilayer perceptions based on the network in network (N1N) architecture, and a restricted Boltzmann machine (RBM). The latter is used for mapping the features to binary codes, and carry out the geometrically invariant correspondence matching task. Our experimental results on several benchmark datasets (e.g., Brown, Oxford, Paris, INRIA Holidays, RomcPatchcs, IIPatches, and CIFAR-10) show that the proposed approach produces the learned binary descriptor that outperforms other baseline self-su per vised binary descriptors in terms of correspondence matching despite the smaller size of its DNN. Most importantly, the proposed approach does not freeze the features that are obtained while pre-training the N1N model. Instead, it line tunes the features while learning the features needed for binary mapping through the RBM. Additionally, its lightweight architecture makes it suitable for resource-constrained devices. Wed, 01 Jan 2020 00:00:00 GMT http://dr.lib.sjp.ac.lk/handle/123456789/9025 2020-01-01T00:00:00Z http://dr.lib.sjp.ac.lk/handle/123456789/8406 Solving systems of nonlinear equations using a modified firefly algorithm (MODFA) Ariyaratne, M.K.A.; Fernando, T.G.I.; Weerakoon, S Tue, 01 Jan 2019 00:00:00 GMT http://dr.lib.sjp.ac.lk/handle/123456789/8406 2019-01-01T00:00:00Z http://dr.lib.sjp.ac.lk/handle/123456789/6975 Animation of Fingerspelled Words and Number Signs of the Sinhala Sign Language Meegama, R.G.N.; Punchimudiyanse, M. Attached; Sign language is the primary communication medium of the aurally handicapped community. Often, a sign gesture is mapped to a word or a phrase in a spoken language and named as a conversational sign. A fingerspelling sign is a special sign derived to show a single character that matches a character in the alphabet of a given language. This enables the deaf community to express words that do not have a conversational sign, such as a name, using a letter-bv-letter technique. Sinhala Sign Language (SSL) uses a phonetic pronunciation mechanism to decode such words due to the presence of one or more modifiers after a consonant. Expressing numbers also have a similar notation, and it is broken down into parts before interpretation in sign gestures. This article presents the variations implemented to make the 3D avatar-based interpreter system look similar to an actual fingerspelled SSL by a human interpreter. To accomplish the task, a phonetic English-based 3D avatar animation system is developed with Blender animation software. The conversion of Sinhala Unicode text to phonetic English and numbers written in digits to sign gestures is done with a Visual Basic.NET (VB.NET) application. The presented application has 61 SSL fingerspelling signs and 40 SSL number signs. It is capable of interpreting any word written using the modern Sinhala alphabet without conversational signs and interprets the numbers that go up to the billions. This is a helpful tool in teaching SSL fingerspelling and number signs of SSL to deaf children. Fri, 01 Sep 2017 00:00:00 GMT http://dr.lib.sjp.ac.lk/handle/123456789/6975 2017-09-01T00:00:00Z http://dr.lib.sjp.ac.lk/handle/123456789/6957 Weerakoon-Fernando Method with accelerated third-order convergence for systems of nonlinear equations Nishani, H.P.S.; Weerakoon, S.; Fernando, T.G.I.; Liyanage, M. Attached; Weerakoon-Fernando Method (WFM) is a widely accepted third order iterative method introduced in the late 1990s to solve nonlinear equations. Even though it has become so popular among numerical analysts resulting in hundreds of similar work for single variable case, after nearly two decades, nobody took the challenge of extending the method to multivariable systems. In this paper, we extend the WFM to functions of several variables and provide a rigorous proof for the third order convergence. This theory was supported by computational results using several systems of nonlinear equations. Computational algorithms were implemented using MATLAB. We further analyse the method mathematically and demonstrate the reason for the strong performance of WFM computationally, despite it requiring more function evaluations. Mon, 01 Jan 2018 00:00:00 GMT http://dr.lib.sjp.ac.lk/handle/123456789/6957 2018-01-01T00:00:00Z