<tool id="rfove" name="Perform segmentation using region-based fitting of overlapping ellipses" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="20.05">
    <description>with RFOVE</description>
    <macros>
        <import>creators.xml</import>
        <import>tests.xml</import>
        <token name="@TOOL_VERSION@">2023.11.12</token>
        <token name="@VERSION_SUFFIX@">2</token>
    </macros>
    <creator>
        <expand macro="creators/bmcv"/>
    </creator>
    <edam_operations>
        <edam_operation>operation_3443</edam_operation>
    </edam_operations>
    <xrefs>
        <xref type="bio.tools">rfove</xref>
    </xrefs>
    <requirements> 
        <container type="docker">docker.io/kostrykin/rfove:@TOOL_VERSION@</container>
    </requirements>
    <command detect_errors="aggressive">
    <![CDATA[
    #set $neighborhood_size = "%d" % ($half_neighborhood_size.value * 2 + 1)
    /rfove
        ${area_ub}
        ${min_area_max_area_ratio_ub}
        ${overlap_ub}
        ${neighborhood_size}
        '${dataset}'

        output.tiff
    ]]>
    </command>
    <inputs>
        <param name="dataset" type="data" format="tiff,png" label="Input image" />
        <param name="area_ub" type="integer" label="Maximum ellipse area" min="5" value="250" />
        <param name="min_area_max_area_ratio_ub" type="float" min="0" max="1" value="0.1" label="Upper bound of the ratio: minimum area / maximum area" />

        <param name="overlap_ub" type="float" label="Maximum ellipse overlap" min="0" value="0.2" />
        <param name="half_neighborhood_size" type="integer" label="Half neighborhood size" min="1" value="100" />
    </inputs>
    <outputs>
        <data format="tiff" name="masks" from_work_dir="output.tiff" label="${tool.name} on ${on_string}" />
    </outputs>
    <tests>
        <test>
            <param name="dataset" value="BBBC033_C2_z28.png" />
            <expand macro="tests/label_image_diff" name="masks" value="output.tiff" ftype="tiff"/>
        </test>
    </tests>
    <help>

        **Perform segmentation using shape decomposition based on elliptical models and expectation maximization.**

        RFOVE is completely unsupervised, operates without any assumption or prior knowledge on the object's shape
        and extends and improves the *Decremental Ellipse Fitting Algorithm* (DEFA). Both RFOVE and DEFA solve the
        multi-ellipse fitting problem by performing model selection that is guided by the minimization of the
        *Akaike Information Criterion* on a suitably defined shape complexity measure. However, in contrast to
        DEFA, RFOVE minimizes an objective function that allows for ellipses with higher degree of overlap and,
        thus, achieves better ellipse-based shape approximation.

    </help>
    <citations>
        <citation type="doi">10.1016/j.imavis.2019.09.001</citation>
    </citations>
</tool>