<?xml version="1.0" encoding="UTF-8"?><?xml-stylesheet type="text/xsl" href="static/style.xsl"?><OAI-PMH xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/ http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd"><responseDate>2026-11-21T06:49:57Z</responseDate><request verb="GetRecord" identifier="oai:macsphere.mcmaster.ca:11375/27125" metadataPrefix="dim">https://prod-ms-be.lib.mcmaster.ca/server/oai/request</request><GetRecord><record><header><identifier>oai:macsphere.mcmaster.ca:11375/27125</identifier><datestamp>2026-09-24T22:26:37Z</datestamp><setSpec>com_11375_271</setSpec><setSpec>col_11375_272</setSpec></header><metadata><dim:dim xmlns:dim="http://www.dspace.org/xmlns/dspace/dim" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:doc="http://www.lyncode.com/xoai" xsi:schemaLocation="http://www.dspace.org/xmlns/dspace/dim http://www.dspace.org/schema/dim.xsd">
   <dim:field mdschema="dc" element="contributor" qualifier="advisor">Chen, Jun</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="author">Wu, Zijun</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="department" lang="en_US">Electrical and Computer Engineering</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="accessioned">2021-10-25T20:31:55Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="available">2021-10-25T20:31:55Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="issued">2021</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">http://hdl.handle.net/11375/27125</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">https://doi.org/10.71548/10368</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="abstract" lang="en_US">Since the problem of image dehazing is of great significance and challenging, it has&#xd;
attracted many researchers for a long time. Many excellent dehazing algorithms have&#xd;
emerged one after another. However, few works focus on dehazing tasks with colour&#xd;
deviations. Existing methods do not perform as well as expected on real image dehazing,&#xd;
especially on images with colour deviations. The proposed method mainly focuses on&#xd;
this task and achieves competitive performance. In this paper, a two-step network is&#xd;
proposed, which consists of the Colour Balance Module and the Dehazing Module. Hazy&#xd;
images are first fed into the Colour Balance Module to generate colour corrected hazy&#xd;
images, which are then sent to the pre-trained dehazing net to get the real colour corrected&#xd;
haze-free results. A coloured haze image database is also constructed. Experiments and&#xd;
comparisons are implemented to show the effectiveness of the proposed method, not&#xd;
only on real coloured-haze images but also on other dehazing tasks.</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="degreetype" lang="en_US">Thesis</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="degree" lang="en_US">Master of Applied Science (MASc)</dim:field>
   <dim:field mdschema="dc" element="language" qualifier="iso" lang="en_US">en</dim:field>
   <dim:field mdschema="dc" element="title" lang="en_US">Single image dehazing for real colored-haze images</dim:field>
   <dim:field mdschema="dc" element="type" lang="en_US">Thesis</dim:field>
   <dim:field mdschema="others" element="access-status">open.access</dim:field>
</dim:dim></metadata></record></GetRecord></OAI-PMH>